Qwen2.5-7B-Instruct_Long_CoT / trainer_state.json
TaiGary's picture
Add files using upload-large-folder tool
8841a78 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 200,
"global_step": 1334,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0014992503748125937,
"grad_norm": 5.832151292802266,
"learning_rate": 9.999986134743949e-06,
"loss": 0.5922,
"step": 1
},
{
"epoch": 0.0029985007496251873,
"grad_norm": 3.313562711862917,
"learning_rate": 9.99994453905269e-06,
"loss": 0.5035,
"step": 2
},
{
"epoch": 0.004497751124437781,
"grad_norm": 3.8053612317508647,
"learning_rate": 9.999875213156919e-06,
"loss": 0.4852,
"step": 3
},
{
"epoch": 0.005997001499250375,
"grad_norm": 2.975780829326707,
"learning_rate": 9.999778157441126e-06,
"loss": 0.448,
"step": 4
},
{
"epoch": 0.0074962518740629685,
"grad_norm": 3.4745434712688645,
"learning_rate": 9.99965337244359e-06,
"loss": 0.4017,
"step": 5
},
{
"epoch": 0.008995502248875561,
"grad_norm": 2.766265131790075,
"learning_rate": 9.999500858856382e-06,
"loss": 0.444,
"step": 6
},
{
"epoch": 0.010494752623688156,
"grad_norm": 2.87369120054187,
"learning_rate": 9.999320617525356e-06,
"loss": 0.4082,
"step": 7
},
{
"epoch": 0.01199400299850075,
"grad_norm": 2.5779601980173705,
"learning_rate": 9.999112649450154e-06,
"loss": 0.424,
"step": 8
},
{
"epoch": 0.013493253373313344,
"grad_norm": 2.535823912227413,
"learning_rate": 9.998876955784183e-06,
"loss": 0.3131,
"step": 9
},
{
"epoch": 0.014992503748125937,
"grad_norm": 2.4492135913471715,
"learning_rate": 9.998613537834625e-06,
"loss": 0.3823,
"step": 10
},
{
"epoch": 0.01649175412293853,
"grad_norm": 2.4404067828272082,
"learning_rate": 9.998322397062426e-06,
"loss": 0.4054,
"step": 11
},
{
"epoch": 0.017991004497751123,
"grad_norm": 2.0448103433799005,
"learning_rate": 9.99800353508228e-06,
"loss": 0.3606,
"step": 12
},
{
"epoch": 0.019490254872563718,
"grad_norm": 2.0734295930755224,
"learning_rate": 9.997656953662627e-06,
"loss": 0.3122,
"step": 13
},
{
"epoch": 0.020989505247376312,
"grad_norm": 2.643785230749524,
"learning_rate": 9.997282654725645e-06,
"loss": 0.4157,
"step": 14
},
{
"epoch": 0.022488755622188907,
"grad_norm": 2.146621645771915,
"learning_rate": 9.996880640347234e-06,
"loss": 0.3606,
"step": 15
},
{
"epoch": 0.0239880059970015,
"grad_norm": 1.826987060952611,
"learning_rate": 9.99645091275701e-06,
"loss": 0.3106,
"step": 16
},
{
"epoch": 0.025487256371814093,
"grad_norm": 2.2986446834557355,
"learning_rate": 9.99599347433828e-06,
"loss": 0.3963,
"step": 17
},
{
"epoch": 0.026986506746626688,
"grad_norm": 2.3216100116981404,
"learning_rate": 9.99550832762805e-06,
"loss": 0.3858,
"step": 18
},
{
"epoch": 0.02848575712143928,
"grad_norm": 1.6900482709514875,
"learning_rate": 9.99499547531699e-06,
"loss": 0.3069,
"step": 19
},
{
"epoch": 0.029985007496251874,
"grad_norm": 2.310364169428319,
"learning_rate": 9.994454920249433e-06,
"loss": 0.3772,
"step": 20
},
{
"epoch": 0.031484257871064465,
"grad_norm": 2.530397424165797,
"learning_rate": 9.993886665423348e-06,
"loss": 0.3945,
"step": 21
},
{
"epoch": 0.03298350824587706,
"grad_norm": 2.1745390028353384,
"learning_rate": 9.993290713990343e-06,
"loss": 0.3738,
"step": 22
},
{
"epoch": 0.034482758620689655,
"grad_norm": 1.8943278042394813,
"learning_rate": 9.99266706925562e-06,
"loss": 0.3807,
"step": 23
},
{
"epoch": 0.035982008995502246,
"grad_norm": 2.187296861936023,
"learning_rate": 9.992015734677979e-06,
"loss": 0.3541,
"step": 24
},
{
"epoch": 0.037481259370314844,
"grad_norm": 2.0547900805990653,
"learning_rate": 9.991336713869785e-06,
"loss": 0.3704,
"step": 25
},
{
"epoch": 0.038980509745127435,
"grad_norm": 1.6612216696005873,
"learning_rate": 9.99063001059696e-06,
"loss": 0.3086,
"step": 26
},
{
"epoch": 0.04047976011994003,
"grad_norm": 2.0346781109199727,
"learning_rate": 9.989895628778952e-06,
"loss": 0.3637,
"step": 27
},
{
"epoch": 0.041979010494752625,
"grad_norm": 1.9918388801867348,
"learning_rate": 9.989133572488716e-06,
"loss": 0.2998,
"step": 28
},
{
"epoch": 0.043478260869565216,
"grad_norm": 2.090041625605034,
"learning_rate": 9.988343845952697e-06,
"loss": 0.3417,
"step": 29
},
{
"epoch": 0.044977511244377814,
"grad_norm": 1.6921443817720527,
"learning_rate": 9.987526453550798e-06,
"loss": 0.3008,
"step": 30
},
{
"epoch": 0.046476761619190406,
"grad_norm": 1.9721881389502063,
"learning_rate": 9.98668139981636e-06,
"loss": 0.3079,
"step": 31
},
{
"epoch": 0.047976011994003,
"grad_norm": 2.034680286190636,
"learning_rate": 9.98580868943614e-06,
"loss": 0.3908,
"step": 32
},
{
"epoch": 0.049475262368815595,
"grad_norm": 1.814883175859987,
"learning_rate": 9.984908327250278e-06,
"loss": 0.2917,
"step": 33
},
{
"epoch": 0.050974512743628186,
"grad_norm": 1.5888369679528016,
"learning_rate": 9.983980318252274e-06,
"loss": 0.2904,
"step": 34
},
{
"epoch": 0.05247376311844078,
"grad_norm": 1.6870813628116277,
"learning_rate": 9.983024667588961e-06,
"loss": 0.3447,
"step": 35
},
{
"epoch": 0.053973013493253376,
"grad_norm": 1.659882359445096,
"learning_rate": 9.982041380560476e-06,
"loss": 0.3281,
"step": 36
},
{
"epoch": 0.05547226386806597,
"grad_norm": 1.7935822097403369,
"learning_rate": 9.98103046262023e-06,
"loss": 0.317,
"step": 37
},
{
"epoch": 0.05697151424287856,
"grad_norm": 1.8433431515779493,
"learning_rate": 9.979991919374877e-06,
"loss": 0.3631,
"step": 38
},
{
"epoch": 0.05847076461769116,
"grad_norm": 1.7345926587775797,
"learning_rate": 9.978925756584284e-06,
"loss": 0.3836,
"step": 39
},
{
"epoch": 0.05997001499250375,
"grad_norm": 1.9585133082499135,
"learning_rate": 9.9778319801615e-06,
"loss": 0.294,
"step": 40
},
{
"epoch": 0.06146926536731634,
"grad_norm": 1.9811955579650895,
"learning_rate": 9.976710596172721e-06,
"loss": 0.3655,
"step": 41
},
{
"epoch": 0.06296851574212893,
"grad_norm": 2.160259859236746,
"learning_rate": 9.975561610837254e-06,
"loss": 0.3146,
"step": 42
},
{
"epoch": 0.06446776611694154,
"grad_norm": 1.7207751114701895,
"learning_rate": 9.974385030527496e-06,
"loss": 0.3133,
"step": 43
},
{
"epoch": 0.06596701649175413,
"grad_norm": 1.7855443710047219,
"learning_rate": 9.973180861768874e-06,
"loss": 0.309,
"step": 44
},
{
"epoch": 0.06746626686656672,
"grad_norm": 1.8337376722089804,
"learning_rate": 9.971949111239838e-06,
"loss": 0.3603,
"step": 45
},
{
"epoch": 0.06896551724137931,
"grad_norm": 1.7686355552580748,
"learning_rate": 9.970689785771798e-06,
"loss": 0.3572,
"step": 46
},
{
"epoch": 0.0704647676161919,
"grad_norm": 1.78765448122615,
"learning_rate": 9.969402892349105e-06,
"loss": 0.347,
"step": 47
},
{
"epoch": 0.07196401799100449,
"grad_norm": 1.4875519550906255,
"learning_rate": 9.968088438109002e-06,
"loss": 0.2704,
"step": 48
},
{
"epoch": 0.0734632683658171,
"grad_norm": 1.9732499378428838,
"learning_rate": 9.966746430341584e-06,
"loss": 0.3503,
"step": 49
},
{
"epoch": 0.07496251874062969,
"grad_norm": 2.146905541628959,
"learning_rate": 9.965376876489765e-06,
"loss": 0.3623,
"step": 50
},
{
"epoch": 0.07646176911544228,
"grad_norm": 1.614927659858716,
"learning_rate": 9.963979784149232e-06,
"loss": 0.3578,
"step": 51
},
{
"epoch": 0.07796101949025487,
"grad_norm": 1.8675950039847051,
"learning_rate": 9.962555161068401e-06,
"loss": 0.3507,
"step": 52
},
{
"epoch": 0.07946026986506746,
"grad_norm": 1.7892287490203982,
"learning_rate": 9.961103015148376e-06,
"loss": 0.3334,
"step": 53
},
{
"epoch": 0.08095952023988005,
"grad_norm": 1.5076155316622697,
"learning_rate": 9.95962335444291e-06,
"loss": 0.283,
"step": 54
},
{
"epoch": 0.08245877061469266,
"grad_norm": 1.8423707803571059,
"learning_rate": 9.958116187158351e-06,
"loss": 0.3306,
"step": 55
},
{
"epoch": 0.08395802098950525,
"grad_norm": 1.8659065819141958,
"learning_rate": 9.956581521653604e-06,
"loss": 0.3626,
"step": 56
},
{
"epoch": 0.08545727136431784,
"grad_norm": 1.9384444327564434,
"learning_rate": 9.955019366440082e-06,
"loss": 0.3544,
"step": 57
},
{
"epoch": 0.08695652173913043,
"grad_norm": 1.9518720846770397,
"learning_rate": 9.953429730181653e-06,
"loss": 0.3983,
"step": 58
},
{
"epoch": 0.08845577211394302,
"grad_norm": 1.315338496772981,
"learning_rate": 9.95181262169461e-06,
"loss": 0.2553,
"step": 59
},
{
"epoch": 0.08995502248875563,
"grad_norm": 1.6617025672603152,
"learning_rate": 9.950168049947597e-06,
"loss": 0.3174,
"step": 60
},
{
"epoch": 0.09145427286356822,
"grad_norm": 1.737723627580491,
"learning_rate": 9.948496024061577e-06,
"loss": 0.3343,
"step": 61
},
{
"epoch": 0.09295352323838081,
"grad_norm": 1.7785564379947172,
"learning_rate": 9.94679655330978e-06,
"loss": 0.3968,
"step": 62
},
{
"epoch": 0.0944527736131934,
"grad_norm": 1.803424330169469,
"learning_rate": 9.945069647117645e-06,
"loss": 0.3156,
"step": 63
},
{
"epoch": 0.095952023988006,
"grad_norm": 1.9221269098368197,
"learning_rate": 9.943315315062766e-06,
"loss": 0.3868,
"step": 64
},
{
"epoch": 0.09745127436281859,
"grad_norm": 1.4963224653122351,
"learning_rate": 9.941533566874852e-06,
"loss": 0.2264,
"step": 65
},
{
"epoch": 0.09895052473763119,
"grad_norm": 1.8089627331199123,
"learning_rate": 9.939724412435661e-06,
"loss": 0.3716,
"step": 66
},
{
"epoch": 0.10044977511244378,
"grad_norm": 1.3393929513761427,
"learning_rate": 9.937887861778947e-06,
"loss": 0.2538,
"step": 67
},
{
"epoch": 0.10194902548725637,
"grad_norm": 1.772529252578735,
"learning_rate": 9.93602392509041e-06,
"loss": 0.3334,
"step": 68
},
{
"epoch": 0.10344827586206896,
"grad_norm": 1.6891607331667922,
"learning_rate": 9.934132612707631e-06,
"loss": 0.3189,
"step": 69
},
{
"epoch": 0.10494752623688156,
"grad_norm": 1.711007340717859,
"learning_rate": 9.932213935120025e-06,
"loss": 0.3096,
"step": 70
},
{
"epoch": 0.10644677661169415,
"grad_norm": 1.3911686059632464,
"learning_rate": 9.930267902968774e-06,
"loss": 0.2781,
"step": 71
},
{
"epoch": 0.10794602698650675,
"grad_norm": 2.094529457781407,
"learning_rate": 9.928294527046771e-06,
"loss": 0.4166,
"step": 72
},
{
"epoch": 0.10944527736131934,
"grad_norm": 1.927455298606518,
"learning_rate": 9.92629381829856e-06,
"loss": 0.3369,
"step": 73
},
{
"epoch": 0.11094452773613193,
"grad_norm": 2.0073308363605498,
"learning_rate": 9.924265787820279e-06,
"loss": 0.4219,
"step": 74
},
{
"epoch": 0.11244377811094453,
"grad_norm": 1.7638340255071605,
"learning_rate": 9.92221044685959e-06,
"loss": 0.3296,
"step": 75
},
{
"epoch": 0.11394302848575712,
"grad_norm": 1.7951654413405462,
"learning_rate": 9.920127806815627e-06,
"loss": 0.3512,
"step": 76
},
{
"epoch": 0.11544227886056972,
"grad_norm": 1.3789136508692579,
"learning_rate": 9.918017879238922e-06,
"loss": 0.3192,
"step": 77
},
{
"epoch": 0.11694152923538231,
"grad_norm": 1.5745019923018957,
"learning_rate": 9.915880675831352e-06,
"loss": 0.2941,
"step": 78
},
{
"epoch": 0.1184407796101949,
"grad_norm": 1.8636959024858308,
"learning_rate": 9.913716208446067e-06,
"loss": 0.4112,
"step": 79
},
{
"epoch": 0.1199400299850075,
"grad_norm": 1.7872534396339679,
"learning_rate": 9.91152448908742e-06,
"loss": 0.3337,
"step": 80
},
{
"epoch": 0.12143928035982009,
"grad_norm": 1.5591473506124205,
"learning_rate": 9.909305529910917e-06,
"loss": 0.2813,
"step": 81
},
{
"epoch": 0.12293853073463268,
"grad_norm": 1.877826476516608,
"learning_rate": 9.907059343223129e-06,
"loss": 0.3691,
"step": 82
},
{
"epoch": 0.12443778110944528,
"grad_norm": 1.3956477717435558,
"learning_rate": 9.904785941481638e-06,
"loss": 0.2706,
"step": 83
},
{
"epoch": 0.12593703148425786,
"grad_norm": 1.4855070209720886,
"learning_rate": 9.902485337294965e-06,
"loss": 0.2799,
"step": 84
},
{
"epoch": 0.12743628185907047,
"grad_norm": 1.58176239758115,
"learning_rate": 9.900157543422493e-06,
"loss": 0.2709,
"step": 85
},
{
"epoch": 0.12893553223388307,
"grad_norm": 1.775459849416814,
"learning_rate": 9.897802572774407e-06,
"loss": 0.3234,
"step": 86
},
{
"epoch": 0.13043478260869565,
"grad_norm": 1.3990606844842433,
"learning_rate": 9.895420438411616e-06,
"loss": 0.2972,
"step": 87
},
{
"epoch": 0.13193403298350825,
"grad_norm": 1.5166812129501177,
"learning_rate": 9.893011153545679e-06,
"loss": 0.2719,
"step": 88
},
{
"epoch": 0.13343328335832083,
"grad_norm": 1.616277925191225,
"learning_rate": 9.89057473153874e-06,
"loss": 0.3291,
"step": 89
},
{
"epoch": 0.13493253373313344,
"grad_norm": 1.8018886039796154,
"learning_rate": 9.888111185903442e-06,
"loss": 0.3504,
"step": 90
},
{
"epoch": 0.136431784107946,
"grad_norm": 1.9006962566663286,
"learning_rate": 9.885620530302865e-06,
"loss": 0.3651,
"step": 91
},
{
"epoch": 0.13793103448275862,
"grad_norm": 1.7392477925879741,
"learning_rate": 9.883102778550434e-06,
"loss": 0.3203,
"step": 92
},
{
"epoch": 0.13943028485757122,
"grad_norm": 1.5542968522475287,
"learning_rate": 9.880557944609863e-06,
"loss": 0.2724,
"step": 93
},
{
"epoch": 0.1409295352323838,
"grad_norm": 1.7350274457709831,
"learning_rate": 9.877986042595062e-06,
"loss": 0.297,
"step": 94
},
{
"epoch": 0.1424287856071964,
"grad_norm": 1.7460497372438528,
"learning_rate": 9.87538708677006e-06,
"loss": 0.3302,
"step": 95
},
{
"epoch": 0.14392803598200898,
"grad_norm": 1.8124484372389353,
"learning_rate": 9.872761091548933e-06,
"loss": 0.3909,
"step": 96
},
{
"epoch": 0.1454272863568216,
"grad_norm": 1.7120552903315012,
"learning_rate": 9.870108071495721e-06,
"loss": 0.3512,
"step": 97
},
{
"epoch": 0.1469265367316342,
"grad_norm": 1.5110515378145573,
"learning_rate": 9.867428041324345e-06,
"loss": 0.3439,
"step": 98
},
{
"epoch": 0.14842578710644677,
"grad_norm": 1.575901576032094,
"learning_rate": 9.864721015898524e-06,
"loss": 0.2743,
"step": 99
},
{
"epoch": 0.14992503748125938,
"grad_norm": 1.72771796682727,
"learning_rate": 9.861987010231701e-06,
"loss": 0.3792,
"step": 100
},
{
"epoch": 0.15142428785607195,
"grad_norm": 1.677067090009642,
"learning_rate": 9.85922603948695e-06,
"loss": 0.3108,
"step": 101
},
{
"epoch": 0.15292353823088456,
"grad_norm": 1.636594343381385,
"learning_rate": 9.856438118976899e-06,
"loss": 0.3234,
"step": 102
},
{
"epoch": 0.15442278860569716,
"grad_norm": 1.5690756819318563,
"learning_rate": 9.853623264163638e-06,
"loss": 0.2662,
"step": 103
},
{
"epoch": 0.15592203898050974,
"grad_norm": 1.5003127598504868,
"learning_rate": 9.850781490658643e-06,
"loss": 0.3091,
"step": 104
},
{
"epoch": 0.15742128935532235,
"grad_norm": 1.5517017459745142,
"learning_rate": 9.84791281422268e-06,
"loss": 0.3002,
"step": 105
},
{
"epoch": 0.15892053973013492,
"grad_norm": 1.6513578763089052,
"learning_rate": 9.845017250765721e-06,
"loss": 0.3715,
"step": 106
},
{
"epoch": 0.16041979010494753,
"grad_norm": 1.4661710458363477,
"learning_rate": 9.84209481634686e-06,
"loss": 0.3269,
"step": 107
},
{
"epoch": 0.1619190404797601,
"grad_norm": 1.4280739519111159,
"learning_rate": 9.839145527174216e-06,
"loss": 0.2853,
"step": 108
},
{
"epoch": 0.1634182908545727,
"grad_norm": 1.4966618108676135,
"learning_rate": 9.836169399604846e-06,
"loss": 0.2783,
"step": 109
},
{
"epoch": 0.16491754122938532,
"grad_norm": 1.820622143024208,
"learning_rate": 9.833166450144665e-06,
"loss": 0.304,
"step": 110
},
{
"epoch": 0.1664167916041979,
"grad_norm": 1.7348469895307392,
"learning_rate": 9.830136695448334e-06,
"loss": 0.307,
"step": 111
},
{
"epoch": 0.1679160419790105,
"grad_norm": 1.6477380424797046,
"learning_rate": 9.827080152319182e-06,
"loss": 0.3428,
"step": 112
},
{
"epoch": 0.16941529235382308,
"grad_norm": 1.797808391190219,
"learning_rate": 9.823996837709114e-06,
"loss": 0.3205,
"step": 113
},
{
"epoch": 0.17091454272863568,
"grad_norm": 1.5866152873541874,
"learning_rate": 9.820886768718503e-06,
"loss": 0.34,
"step": 114
},
{
"epoch": 0.1724137931034483,
"grad_norm": 1.5259306986626615,
"learning_rate": 9.817749962596115e-06,
"loss": 0.3371,
"step": 115
},
{
"epoch": 0.17391304347826086,
"grad_norm": 1.727311329625642,
"learning_rate": 9.814586436738998e-06,
"loss": 0.3481,
"step": 116
},
{
"epoch": 0.17541229385307347,
"grad_norm": 1.768431243352721,
"learning_rate": 9.811396208692387e-06,
"loss": 0.3234,
"step": 117
},
{
"epoch": 0.17691154422788605,
"grad_norm": 1.7910143368656124,
"learning_rate": 9.808179296149616e-06,
"loss": 0.3131,
"step": 118
},
{
"epoch": 0.17841079460269865,
"grad_norm": 1.6989000545542607,
"learning_rate": 9.804935716952011e-06,
"loss": 0.3384,
"step": 119
},
{
"epoch": 0.17991004497751126,
"grad_norm": 1.6517482708330093,
"learning_rate": 9.801665489088795e-06,
"loss": 0.3314,
"step": 120
},
{
"epoch": 0.18140929535232383,
"grad_norm": 1.9814538682881786,
"learning_rate": 9.798368630696984e-06,
"loss": 0.3509,
"step": 121
},
{
"epoch": 0.18290854572713644,
"grad_norm": 1.6355141459388147,
"learning_rate": 9.795045160061295e-06,
"loss": 0.2916,
"step": 122
},
{
"epoch": 0.18440779610194902,
"grad_norm": 1.589896307882102,
"learning_rate": 9.791695095614036e-06,
"loss": 0.3304,
"step": 123
},
{
"epoch": 0.18590704647676162,
"grad_norm": 1.509494539611863,
"learning_rate": 9.788318455935008e-06,
"loss": 0.2895,
"step": 124
},
{
"epoch": 0.1874062968515742,
"grad_norm": 1.5391621689007515,
"learning_rate": 9.7849152597514e-06,
"loss": 0.2971,
"step": 125
},
{
"epoch": 0.1889055472263868,
"grad_norm": 1.470357069635157,
"learning_rate": 9.781485525937683e-06,
"loss": 0.2687,
"step": 126
},
{
"epoch": 0.1904047976011994,
"grad_norm": 1.6457208798187986,
"learning_rate": 9.778029273515519e-06,
"loss": 0.2895,
"step": 127
},
{
"epoch": 0.191904047976012,
"grad_norm": 1.8946516116602614,
"learning_rate": 9.774546521653633e-06,
"loss": 0.3733,
"step": 128
},
{
"epoch": 0.1934032983508246,
"grad_norm": 1.6233385445584763,
"learning_rate": 9.771037289667726e-06,
"loss": 0.2899,
"step": 129
},
{
"epoch": 0.19490254872563717,
"grad_norm": 1.7229580627088865,
"learning_rate": 9.767501597020357e-06,
"loss": 0.314,
"step": 130
},
{
"epoch": 0.19640179910044978,
"grad_norm": 1.7220790561420378,
"learning_rate": 9.76393946332084e-06,
"loss": 0.3255,
"step": 131
},
{
"epoch": 0.19790104947526238,
"grad_norm": 1.8855841747799418,
"learning_rate": 9.760350908325131e-06,
"loss": 0.3063,
"step": 132
},
{
"epoch": 0.19940029985007496,
"grad_norm": 1.6461515144331846,
"learning_rate": 9.756735951935725e-06,
"loss": 0.3018,
"step": 133
},
{
"epoch": 0.20089955022488756,
"grad_norm": 1.6275566076097705,
"learning_rate": 9.753094614201542e-06,
"loss": 0.2734,
"step": 134
},
{
"epoch": 0.20239880059970014,
"grad_norm": 1.8047506186915083,
"learning_rate": 9.749426915317812e-06,
"loss": 0.3349,
"step": 135
},
{
"epoch": 0.20389805097451275,
"grad_norm": 1.7150541048121033,
"learning_rate": 9.74573287562597e-06,
"loss": 0.3814,
"step": 136
},
{
"epoch": 0.20539730134932535,
"grad_norm": 1.3746356899516263,
"learning_rate": 9.742012515613536e-06,
"loss": 0.2716,
"step": 137
},
{
"epoch": 0.20689655172413793,
"grad_norm": 1.3615297932269776,
"learning_rate": 9.738265855914014e-06,
"loss": 0.2969,
"step": 138
},
{
"epoch": 0.20839580209895053,
"grad_norm": 1.5967914555260672,
"learning_rate": 9.734492917306754e-06,
"loss": 0.3593,
"step": 139
},
{
"epoch": 0.2098950524737631,
"grad_norm": 1.3926414012145243,
"learning_rate": 9.730693720716866e-06,
"loss": 0.3249,
"step": 140
},
{
"epoch": 0.21139430284857572,
"grad_norm": 1.6300854417692394,
"learning_rate": 9.72686828721508e-06,
"loss": 0.3249,
"step": 141
},
{
"epoch": 0.2128935532233883,
"grad_norm": 1.6503747755051488,
"learning_rate": 9.723016638017644e-06,
"loss": 0.3485,
"step": 142
},
{
"epoch": 0.2143928035982009,
"grad_norm": 1.6424580489660745,
"learning_rate": 9.719138794486198e-06,
"loss": 0.3037,
"step": 143
},
{
"epoch": 0.2158920539730135,
"grad_norm": 1.4679460728212463,
"learning_rate": 9.715234778127658e-06,
"loss": 0.2478,
"step": 144
},
{
"epoch": 0.21739130434782608,
"grad_norm": 1.6694203271135328,
"learning_rate": 9.711304610594104e-06,
"loss": 0.3046,
"step": 145
},
{
"epoch": 0.21889055472263869,
"grad_norm": 1.7953365930318501,
"learning_rate": 9.70734831368264e-06,
"loss": 0.3774,
"step": 146
},
{
"epoch": 0.22038980509745126,
"grad_norm": 1.5605081251877446,
"learning_rate": 9.7033659093353e-06,
"loss": 0.2699,
"step": 147
},
{
"epoch": 0.22188905547226387,
"grad_norm": 2.1619847536998766,
"learning_rate": 9.699357419638904e-06,
"loss": 0.3967,
"step": 148
},
{
"epoch": 0.22338830584707647,
"grad_norm": 1.4670650567878318,
"learning_rate": 9.695322866824948e-06,
"loss": 0.2689,
"step": 149
},
{
"epoch": 0.22488755622188905,
"grad_norm": 1.7468328982463712,
"learning_rate": 9.691262273269472e-06,
"loss": 0.3513,
"step": 150
},
{
"epoch": 0.22638680659670166,
"grad_norm": 1.5327358567242733,
"learning_rate": 9.687175661492944e-06,
"loss": 0.302,
"step": 151
},
{
"epoch": 0.22788605697151423,
"grad_norm": 1.2492938609432371,
"learning_rate": 9.683063054160136e-06,
"loss": 0.2079,
"step": 152
},
{
"epoch": 0.22938530734632684,
"grad_norm": 1.801480350197766,
"learning_rate": 9.678924474079986e-06,
"loss": 0.3353,
"step": 153
},
{
"epoch": 0.23088455772113944,
"grad_norm": 1.3819349277061614,
"learning_rate": 9.67475994420548e-06,
"loss": 0.3082,
"step": 154
},
{
"epoch": 0.23238380809595202,
"grad_norm": 1.4854125018298305,
"learning_rate": 9.670569487633534e-06,
"loss": 0.3296,
"step": 155
},
{
"epoch": 0.23388305847076463,
"grad_norm": 1.591721543394339,
"learning_rate": 9.666353127604845e-06,
"loss": 0.3695,
"step": 156
},
{
"epoch": 0.2353823088455772,
"grad_norm": 1.3623438969280577,
"learning_rate": 9.66211088750378e-06,
"loss": 0.2687,
"step": 157
},
{
"epoch": 0.2368815592203898,
"grad_norm": 1.59662021079487,
"learning_rate": 9.657842790858235e-06,
"loss": 0.3131,
"step": 158
},
{
"epoch": 0.2383808095952024,
"grad_norm": 2.103772556104017,
"learning_rate": 9.65354886133951e-06,
"loss": 0.3974,
"step": 159
},
{
"epoch": 0.239880059970015,
"grad_norm": 1.5390373761351863,
"learning_rate": 9.64922912276218e-06,
"loss": 0.3089,
"step": 160
},
{
"epoch": 0.2413793103448276,
"grad_norm": 1.608215555985029,
"learning_rate": 9.644883599083959e-06,
"loss": 0.3104,
"step": 161
},
{
"epoch": 0.24287856071964017,
"grad_norm": 1.6370107777138407,
"learning_rate": 9.640512314405563e-06,
"loss": 0.3083,
"step": 162
},
{
"epoch": 0.24437781109445278,
"grad_norm": 1.720253344356971,
"learning_rate": 9.636115292970587e-06,
"loss": 0.3549,
"step": 163
},
{
"epoch": 0.24587706146926536,
"grad_norm": 1.651830367850379,
"learning_rate": 9.63169255916536e-06,
"loss": 0.2953,
"step": 164
},
{
"epoch": 0.24737631184407796,
"grad_norm": 1.4108283122209617,
"learning_rate": 9.627244137518821e-06,
"loss": 0.2691,
"step": 165
},
{
"epoch": 0.24887556221889057,
"grad_norm": 1.6335828982320395,
"learning_rate": 9.622770052702366e-06,
"loss": 0.3137,
"step": 166
},
{
"epoch": 0.25037481259370314,
"grad_norm": 1.4429157887428632,
"learning_rate": 9.618270329529734e-06,
"loss": 0.2653,
"step": 167
},
{
"epoch": 0.2518740629685157,
"grad_norm": 1.5669347774146625,
"learning_rate": 9.613744992956844e-06,
"loss": 0.2818,
"step": 168
},
{
"epoch": 0.25337331334332835,
"grad_norm": 1.3176035507431232,
"learning_rate": 9.609194068081682e-06,
"loss": 0.2748,
"step": 169
},
{
"epoch": 0.25487256371814093,
"grad_norm": 1.7360622452211882,
"learning_rate": 9.60461758014414e-06,
"loss": 0.3223,
"step": 170
},
{
"epoch": 0.2563718140929535,
"grad_norm": 1.450919912803998,
"learning_rate": 9.60001555452589e-06,
"loss": 0.3199,
"step": 171
},
{
"epoch": 0.25787106446776614,
"grad_norm": 1.5835132895230042,
"learning_rate": 9.595388016750236e-06,
"loss": 0.298,
"step": 172
},
{
"epoch": 0.2593703148425787,
"grad_norm": 1.8234775881833296,
"learning_rate": 9.590734992481978e-06,
"loss": 0.2865,
"step": 173
},
{
"epoch": 0.2608695652173913,
"grad_norm": 1.606177227731814,
"learning_rate": 9.586056507527266e-06,
"loss": 0.3566,
"step": 174
},
{
"epoch": 0.2623688155922039,
"grad_norm": 1.864558112262121,
"learning_rate": 9.581352587833455e-06,
"loss": 0.3244,
"step": 175
},
{
"epoch": 0.2638680659670165,
"grad_norm": 1.8906574630017996,
"learning_rate": 9.576623259488966e-06,
"loss": 0.3849,
"step": 176
},
{
"epoch": 0.2653673163418291,
"grad_norm": 2.102559816803484,
"learning_rate": 9.571868548723137e-06,
"loss": 0.4755,
"step": 177
},
{
"epoch": 0.26686656671664166,
"grad_norm": 1.5774518141152993,
"learning_rate": 9.567088481906084e-06,
"loss": 0.301,
"step": 178
},
{
"epoch": 0.2683658170914543,
"grad_norm": 1.4230003632405575,
"learning_rate": 9.562283085548546e-06,
"loss": 0.2292,
"step": 179
},
{
"epoch": 0.2698650674662669,
"grad_norm": 1.9278458923026665,
"learning_rate": 9.55745238630174e-06,
"loss": 0.3696,
"step": 180
},
{
"epoch": 0.27136431784107945,
"grad_norm": 1.5235483685662072,
"learning_rate": 9.552596410957224e-06,
"loss": 0.3119,
"step": 181
},
{
"epoch": 0.272863568215892,
"grad_norm": 1.4491233510197186,
"learning_rate": 9.547715186446732e-06,
"loss": 0.2845,
"step": 182
},
{
"epoch": 0.27436281859070466,
"grad_norm": 1.5556059068218815,
"learning_rate": 9.542808739842034e-06,
"loss": 0.3402,
"step": 183
},
{
"epoch": 0.27586206896551724,
"grad_norm": 1.6386610105907913,
"learning_rate": 9.537877098354787e-06,
"loss": 0.314,
"step": 184
},
{
"epoch": 0.2773613193403298,
"grad_norm": 1.7958204027789255,
"learning_rate": 9.532920289336378e-06,
"loss": 0.3177,
"step": 185
},
{
"epoch": 0.27886056971514245,
"grad_norm": 1.5112411816887386,
"learning_rate": 9.52793834027778e-06,
"loss": 0.3123,
"step": 186
},
{
"epoch": 0.280359820089955,
"grad_norm": 1.5467545255177493,
"learning_rate": 9.522931278809393e-06,
"loss": 0.348,
"step": 187
},
{
"epoch": 0.2818590704647676,
"grad_norm": 1.5182824026116655,
"learning_rate": 9.517899132700889e-06,
"loss": 0.3076,
"step": 188
},
{
"epoch": 0.28335832083958024,
"grad_norm": 1.4551124701666456,
"learning_rate": 9.512841929861069e-06,
"loss": 0.2654,
"step": 189
},
{
"epoch": 0.2848575712143928,
"grad_norm": 1.726905433944032,
"learning_rate": 9.507759698337698e-06,
"loss": 0.3768,
"step": 190
},
{
"epoch": 0.2863568215892054,
"grad_norm": 1.5251935151222835,
"learning_rate": 9.50265246631735e-06,
"loss": 0.3417,
"step": 191
},
{
"epoch": 0.28785607196401797,
"grad_norm": 1.3344343517454702,
"learning_rate": 9.49752026212526e-06,
"loss": 0.3046,
"step": 192
},
{
"epoch": 0.2893553223388306,
"grad_norm": 1.667291769433292,
"learning_rate": 9.492363114225156e-06,
"loss": 0.4019,
"step": 193
},
{
"epoch": 0.2908545727136432,
"grad_norm": 1.3462565282632641,
"learning_rate": 9.487181051219107e-06,
"loss": 0.2833,
"step": 194
},
{
"epoch": 0.29235382308845576,
"grad_norm": 1.708949142760287,
"learning_rate": 9.481974101847371e-06,
"loss": 0.339,
"step": 195
},
{
"epoch": 0.2938530734632684,
"grad_norm": 1.579905077082289,
"learning_rate": 9.476742294988214e-06,
"loss": 0.2755,
"step": 196
},
{
"epoch": 0.29535232383808097,
"grad_norm": 1.6988933363208567,
"learning_rate": 9.471485659657782e-06,
"loss": 0.3112,
"step": 197
},
{
"epoch": 0.29685157421289354,
"grad_norm": 1.5692224559179928,
"learning_rate": 9.466204225009905e-06,
"loss": 0.2933,
"step": 198
},
{
"epoch": 0.2983508245877061,
"grad_norm": 1.4813487646585581,
"learning_rate": 9.460898020335964e-06,
"loss": 0.3178,
"step": 199
},
{
"epoch": 0.29985007496251875,
"grad_norm": 1.3414890287359442,
"learning_rate": 9.455567075064715e-06,
"loss": 0.278,
"step": 200
},
{
"epoch": 0.29985007496251875,
"eval_loss": 0.31865087151527405,
"eval_runtime": 9.5346,
"eval_samples_per_second": 5.664,
"eval_steps_per_second": 1.468,
"step": 200
},
{
"epoch": 0.30134932533733133,
"grad_norm": 1.2914491820490537,
"learning_rate": 9.450211418762123e-06,
"loss": 0.2545,
"step": 201
},
{
"epoch": 0.3028485757121439,
"grad_norm": 1.617206879004949,
"learning_rate": 9.444831081131209e-06,
"loss": 0.3245,
"step": 202
},
{
"epoch": 0.30434782608695654,
"grad_norm": 1.5879038240403078,
"learning_rate": 9.439426092011877e-06,
"loss": 0.2672,
"step": 203
},
{
"epoch": 0.3058470764617691,
"grad_norm": 1.4721712902504815,
"learning_rate": 9.433996481380747e-06,
"loss": 0.2441,
"step": 204
},
{
"epoch": 0.3073463268365817,
"grad_norm": 1.6851515330584104,
"learning_rate": 9.428542279351e-06,
"loss": 0.3122,
"step": 205
},
{
"epoch": 0.30884557721139433,
"grad_norm": 1.551471086948896,
"learning_rate": 9.423063516172195e-06,
"loss": 0.3125,
"step": 206
},
{
"epoch": 0.3103448275862069,
"grad_norm": 1.541216254933102,
"learning_rate": 9.417560222230115e-06,
"loss": 0.3265,
"step": 207
},
{
"epoch": 0.3118440779610195,
"grad_norm": 1.8241894939272227,
"learning_rate": 9.412032428046594e-06,
"loss": 0.3628,
"step": 208
},
{
"epoch": 0.31334332833583206,
"grad_norm": 1.4585076619859787,
"learning_rate": 9.40648016427934e-06,
"loss": 0.3172,
"step": 209
},
{
"epoch": 0.3148425787106447,
"grad_norm": 1.4947685572204896,
"learning_rate": 9.400903461721783e-06,
"loss": 0.3262,
"step": 210
},
{
"epoch": 0.31634182908545727,
"grad_norm": 1.710479676870878,
"learning_rate": 9.395302351302881e-06,
"loss": 0.3026,
"step": 211
},
{
"epoch": 0.31784107946026985,
"grad_norm": 1.5891445921255554,
"learning_rate": 9.38967686408697e-06,
"loss": 0.3041,
"step": 212
},
{
"epoch": 0.3193403298350825,
"grad_norm": 1.877043820678234,
"learning_rate": 9.384027031273575e-06,
"loss": 0.3651,
"step": 213
},
{
"epoch": 0.32083958020989506,
"grad_norm": 1.6476737455461057,
"learning_rate": 9.37835288419725e-06,
"loss": 0.3274,
"step": 214
},
{
"epoch": 0.32233883058470764,
"grad_norm": 1.4048072633025106,
"learning_rate": 9.372654454327394e-06,
"loss": 0.2915,
"step": 215
},
{
"epoch": 0.3238380809595202,
"grad_norm": 1.5824932612563747,
"learning_rate": 9.366931773268083e-06,
"loss": 0.3424,
"step": 216
},
{
"epoch": 0.32533733133433285,
"grad_norm": 1.4045621444023597,
"learning_rate": 9.361184872757894e-06,
"loss": 0.2994,
"step": 217
},
{
"epoch": 0.3268365817091454,
"grad_norm": 1.6783345093583486,
"learning_rate": 9.355413784669722e-06,
"loss": 0.316,
"step": 218
},
{
"epoch": 0.328335832083958,
"grad_norm": 1.5136120438067788,
"learning_rate": 9.349618541010616e-06,
"loss": 0.2875,
"step": 219
},
{
"epoch": 0.32983508245877063,
"grad_norm": 1.8347656685110798,
"learning_rate": 9.343799173921591e-06,
"loss": 0.3255,
"step": 220
},
{
"epoch": 0.3313343328335832,
"grad_norm": 1.6747537616262171,
"learning_rate": 9.337955715677452e-06,
"loss": 0.3227,
"step": 221
},
{
"epoch": 0.3328335832083958,
"grad_norm": 1.611748954880504,
"learning_rate": 9.332088198686618e-06,
"loss": 0.3494,
"step": 222
},
{
"epoch": 0.3343328335832084,
"grad_norm": 1.3926543986691533,
"learning_rate": 9.326196655490935e-06,
"loss": 0.3003,
"step": 223
},
{
"epoch": 0.335832083958021,
"grad_norm": 1.6253583560543892,
"learning_rate": 9.32028111876551e-06,
"loss": 0.312,
"step": 224
},
{
"epoch": 0.3373313343328336,
"grad_norm": 1.4601075879292786,
"learning_rate": 9.314341621318512e-06,
"loss": 0.3017,
"step": 225
},
{
"epoch": 0.33883058470764615,
"grad_norm": 1.8018907632171013,
"learning_rate": 9.308378196091006e-06,
"loss": 0.394,
"step": 226
},
{
"epoch": 0.3403298350824588,
"grad_norm": 1.5853864532070887,
"learning_rate": 9.302390876156756e-06,
"loss": 0.2828,
"step": 227
},
{
"epoch": 0.34182908545727136,
"grad_norm": 1.3452148779288864,
"learning_rate": 9.296379694722051e-06,
"loss": 0.2827,
"step": 228
},
{
"epoch": 0.34332833583208394,
"grad_norm": 1.310866650589732,
"learning_rate": 9.29034468512552e-06,
"loss": 0.2704,
"step": 229
},
{
"epoch": 0.3448275862068966,
"grad_norm": 1.506333918893538,
"learning_rate": 9.284285880837947e-06,
"loss": 0.3099,
"step": 230
},
{
"epoch": 0.34632683658170915,
"grad_norm": 1.490555616381991,
"learning_rate": 9.278203315462078e-06,
"loss": 0.2802,
"step": 231
},
{
"epoch": 0.34782608695652173,
"grad_norm": 1.3759927570780872,
"learning_rate": 9.272097022732444e-06,
"loss": 0.269,
"step": 232
},
{
"epoch": 0.3493253373313343,
"grad_norm": 1.5108818707437988,
"learning_rate": 9.26596703651517e-06,
"loss": 0.2963,
"step": 233
},
{
"epoch": 0.35082458770614694,
"grad_norm": 1.6364308232242346,
"learning_rate": 9.259813390807788e-06,
"loss": 0.3649,
"step": 234
},
{
"epoch": 0.3523238380809595,
"grad_norm": 1.6168540956790163,
"learning_rate": 9.253636119739046e-06,
"loss": 0.2944,
"step": 235
},
{
"epoch": 0.3538230884557721,
"grad_norm": 1.587020700255697,
"learning_rate": 9.247435257568724e-06,
"loss": 0.3142,
"step": 236
},
{
"epoch": 0.3553223388305847,
"grad_norm": 1.5298114520922985,
"learning_rate": 9.241210838687438e-06,
"loss": 0.3315,
"step": 237
},
{
"epoch": 0.3568215892053973,
"grad_norm": 1.6335252140407155,
"learning_rate": 9.23496289761645e-06,
"loss": 0.3397,
"step": 238
},
{
"epoch": 0.3583208395802099,
"grad_norm": 1.674399202898891,
"learning_rate": 9.228691469007487e-06,
"loss": 0.3516,
"step": 239
},
{
"epoch": 0.3598200899550225,
"grad_norm": 1.7823402906317811,
"learning_rate": 9.222396587642528e-06,
"loss": 0.3502,
"step": 240
},
{
"epoch": 0.3613193403298351,
"grad_norm": 1.4099094018415357,
"learning_rate": 9.216078288433632e-06,
"loss": 0.3187,
"step": 241
},
{
"epoch": 0.36281859070464767,
"grad_norm": 1.8182655020498848,
"learning_rate": 9.209736606422736e-06,
"loss": 0.3157,
"step": 242
},
{
"epoch": 0.36431784107946025,
"grad_norm": 1.7687977513877544,
"learning_rate": 9.203371576781457e-06,
"loss": 0.335,
"step": 243
},
{
"epoch": 0.3658170914542729,
"grad_norm": 1.483158152454702,
"learning_rate": 9.1969832348109e-06,
"loss": 0.298,
"step": 244
},
{
"epoch": 0.36731634182908546,
"grad_norm": 1.4043101733884487,
"learning_rate": 9.190571615941462e-06,
"loss": 0.3012,
"step": 245
},
{
"epoch": 0.36881559220389803,
"grad_norm": 1.4752437511712757,
"learning_rate": 9.18413675573264e-06,
"loss": 0.3182,
"step": 246
},
{
"epoch": 0.37031484257871067,
"grad_norm": 1.6533133805844158,
"learning_rate": 9.177678689872831e-06,
"loss": 0.3766,
"step": 247
},
{
"epoch": 0.37181409295352325,
"grad_norm": 1.3475127139058065,
"learning_rate": 9.171197454179124e-06,
"loss": 0.3069,
"step": 248
},
{
"epoch": 0.3733133433283358,
"grad_norm": 1.4956515930266987,
"learning_rate": 9.16469308459712e-06,
"loss": 0.3195,
"step": 249
},
{
"epoch": 0.3748125937031484,
"grad_norm": 1.554696970967648,
"learning_rate": 9.158165617200717e-06,
"loss": 0.3165,
"step": 250
},
{
"epoch": 0.37631184407796103,
"grad_norm": 1.4803392008015672,
"learning_rate": 9.151615088191918e-06,
"loss": 0.2986,
"step": 251
},
{
"epoch": 0.3778110944527736,
"grad_norm": 1.4012614689308533,
"learning_rate": 9.14504153390063e-06,
"loss": 0.2783,
"step": 252
},
{
"epoch": 0.3793103448275862,
"grad_norm": 1.5532716690880104,
"learning_rate": 9.138444990784455e-06,
"loss": 0.3668,
"step": 253
},
{
"epoch": 0.3808095952023988,
"grad_norm": 1.5900316421763145,
"learning_rate": 9.131825495428496e-06,
"loss": 0.3149,
"step": 254
},
{
"epoch": 0.3823088455772114,
"grad_norm": 1.4731630574906363,
"learning_rate": 9.125183084545158e-06,
"loss": 0.3242,
"step": 255
},
{
"epoch": 0.383808095952024,
"grad_norm": 1.8078183568590966,
"learning_rate": 9.118517794973925e-06,
"loss": 0.3534,
"step": 256
},
{
"epoch": 0.3853073463268366,
"grad_norm": 1.3669095909006088,
"learning_rate": 9.111829663681182e-06,
"loss": 0.3017,
"step": 257
},
{
"epoch": 0.3868065967016492,
"grad_norm": 1.4104333598522873,
"learning_rate": 9.105118727759984e-06,
"loss": 0.3089,
"step": 258
},
{
"epoch": 0.38830584707646176,
"grad_norm": 1.8586145483699874,
"learning_rate": 9.098385024429875e-06,
"loss": 0.3085,
"step": 259
},
{
"epoch": 0.38980509745127434,
"grad_norm": 1.4223222044665933,
"learning_rate": 9.09162859103666e-06,
"loss": 0.3244,
"step": 260
},
{
"epoch": 0.391304347826087,
"grad_norm": 1.884873876770662,
"learning_rate": 9.08484946505221e-06,
"loss": 0.3837,
"step": 261
},
{
"epoch": 0.39280359820089955,
"grad_norm": 1.7983916583732078,
"learning_rate": 9.078047684074254e-06,
"loss": 0.3546,
"step": 262
},
{
"epoch": 0.39430284857571213,
"grad_norm": 1.4502714296949408,
"learning_rate": 9.071223285826166e-06,
"loss": 0.2613,
"step": 263
},
{
"epoch": 0.39580209895052476,
"grad_norm": 1.6815524788277352,
"learning_rate": 9.064376308156754e-06,
"loss": 0.3553,
"step": 264
},
{
"epoch": 0.39730134932533734,
"grad_norm": 1.6792700035651802,
"learning_rate": 9.057506789040063e-06,
"loss": 0.3332,
"step": 265
},
{
"epoch": 0.3988005997001499,
"grad_norm": 1.7631646154436653,
"learning_rate": 9.050614766575147e-06,
"loss": 0.3745,
"step": 266
},
{
"epoch": 0.4002998500749625,
"grad_norm": 1.3326861130696177,
"learning_rate": 9.043700278985867e-06,
"loss": 0.2829,
"step": 267
},
{
"epoch": 0.4017991004497751,
"grad_norm": 1.5373974839212117,
"learning_rate": 9.03676336462068e-06,
"loss": 0.3159,
"step": 268
},
{
"epoch": 0.4032983508245877,
"grad_norm": 1.4848523958607267,
"learning_rate": 9.029804061952426e-06,
"loss": 0.2817,
"step": 269
},
{
"epoch": 0.4047976011994003,
"grad_norm": 1.4186378261482933,
"learning_rate": 9.022822409578106e-06,
"loss": 0.3007,
"step": 270
},
{
"epoch": 0.4062968515742129,
"grad_norm": 1.3665551190637126,
"learning_rate": 9.015818446218683e-06,
"loss": 0.2663,
"step": 271
},
{
"epoch": 0.4077961019490255,
"grad_norm": 1.8004513614500592,
"learning_rate": 9.008792210718854e-06,
"loss": 0.3166,
"step": 272
},
{
"epoch": 0.40929535232383807,
"grad_norm": 1.7271025597363883,
"learning_rate": 9.00174374204684e-06,
"loss": 0.3985,
"step": 273
},
{
"epoch": 0.4107946026986507,
"grad_norm": 1.7120420253419553,
"learning_rate": 8.994673079294171e-06,
"loss": 0.2887,
"step": 274
},
{
"epoch": 0.4122938530734633,
"grad_norm": 1.5573334644227972,
"learning_rate": 8.987580261675466e-06,
"loss": 0.3118,
"step": 275
},
{
"epoch": 0.41379310344827586,
"grad_norm": 1.7532970724016852,
"learning_rate": 8.98046532852822e-06,
"loss": 0.3451,
"step": 276
},
{
"epoch": 0.41529235382308843,
"grad_norm": 1.7990888104381544,
"learning_rate": 8.973328319312577e-06,
"loss": 0.378,
"step": 277
},
{
"epoch": 0.41679160419790107,
"grad_norm": 1.3765160345020095,
"learning_rate": 8.966169273611125e-06,
"loss": 0.2431,
"step": 278
},
{
"epoch": 0.41829085457271364,
"grad_norm": 1.7424289558232744,
"learning_rate": 8.958988231128665e-06,
"loss": 0.3395,
"step": 279
},
{
"epoch": 0.4197901049475262,
"grad_norm": 1.5102284530060985,
"learning_rate": 8.95178523169199e-06,
"loss": 0.3121,
"step": 280
},
{
"epoch": 0.42128935532233885,
"grad_norm": 1.423068646962132,
"learning_rate": 8.944560315249676e-06,
"loss": 0.2699,
"step": 281
},
{
"epoch": 0.42278860569715143,
"grad_norm": 1.2082261571628317,
"learning_rate": 8.937313521871846e-06,
"loss": 0.2766,
"step": 282
},
{
"epoch": 0.424287856071964,
"grad_norm": 1.6368109030503832,
"learning_rate": 8.930044891749962e-06,
"loss": 0.318,
"step": 283
},
{
"epoch": 0.4257871064467766,
"grad_norm": 1.6853820955568977,
"learning_rate": 8.922754465196591e-06,
"loss": 0.2909,
"step": 284
},
{
"epoch": 0.4272863568215892,
"grad_norm": 1.4242235536170476,
"learning_rate": 8.915442282645183e-06,
"loss": 0.299,
"step": 285
},
{
"epoch": 0.4287856071964018,
"grad_norm": 1.4956901901699613,
"learning_rate": 8.908108384649856e-06,
"loss": 0.2931,
"step": 286
},
{
"epoch": 0.4302848575712144,
"grad_norm": 1.4522693723774607,
"learning_rate": 8.900752811885152e-06,
"loss": 0.2998,
"step": 287
},
{
"epoch": 0.431784107946027,
"grad_norm": 1.3862849952507832,
"learning_rate": 8.893375605145837e-06,
"loss": 0.2787,
"step": 288
},
{
"epoch": 0.4332833583208396,
"grad_norm": 1.3759797800861127,
"learning_rate": 8.885976805346651e-06,
"loss": 0.3469,
"step": 289
},
{
"epoch": 0.43478260869565216,
"grad_norm": 1.6160672226143369,
"learning_rate": 8.8785564535221e-06,
"loss": 0.3484,
"step": 290
},
{
"epoch": 0.4362818590704648,
"grad_norm": 1.8236449668128274,
"learning_rate": 8.871114590826211e-06,
"loss": 0.3252,
"step": 291
},
{
"epoch": 0.43778110944527737,
"grad_norm": 2.0215149861497417,
"learning_rate": 8.86365125853232e-06,
"loss": 0.3041,
"step": 292
},
{
"epoch": 0.43928035982008995,
"grad_norm": 1.4226330217038914,
"learning_rate": 8.85616649803283e-06,
"loss": 0.3237,
"step": 293
},
{
"epoch": 0.4407796101949025,
"grad_norm": 1.3243895047996546,
"learning_rate": 8.84866035083899e-06,
"loss": 0.2351,
"step": 294
},
{
"epoch": 0.44227886056971516,
"grad_norm": 1.338019694505218,
"learning_rate": 8.841132858580661e-06,
"loss": 0.2858,
"step": 295
},
{
"epoch": 0.44377811094452774,
"grad_norm": 1.541795435962147,
"learning_rate": 8.833584063006088e-06,
"loss": 0.3136,
"step": 296
},
{
"epoch": 0.4452773613193403,
"grad_norm": 1.8246954956049057,
"learning_rate": 8.826014005981662e-06,
"loss": 0.3781,
"step": 297
},
{
"epoch": 0.44677661169415295,
"grad_norm": 1.5281229728644417,
"learning_rate": 8.818422729491693e-06,
"loss": 0.2583,
"step": 298
},
{
"epoch": 0.4482758620689655,
"grad_norm": 1.588026816491082,
"learning_rate": 8.810810275638183e-06,
"loss": 0.3067,
"step": 299
},
{
"epoch": 0.4497751124437781,
"grad_norm": 1.3942715313521852,
"learning_rate": 8.803176686640577e-06,
"loss": 0.2353,
"step": 300
},
{
"epoch": 0.4512743628185907,
"grad_norm": 1.4891178081833167,
"learning_rate": 8.795522004835543e-06,
"loss": 0.3063,
"step": 301
},
{
"epoch": 0.4527736131934033,
"grad_norm": 1.4962818451621016,
"learning_rate": 8.787846272676728e-06,
"loss": 0.3081,
"step": 302
},
{
"epoch": 0.4542728635682159,
"grad_norm": 1.3436327405802937,
"learning_rate": 8.780149532734531e-06,
"loss": 0.2847,
"step": 303
},
{
"epoch": 0.45577211394302847,
"grad_norm": 1.4513621866632591,
"learning_rate": 8.772431827695862e-06,
"loss": 0.3314,
"step": 304
},
{
"epoch": 0.4572713643178411,
"grad_norm": 1.4846215391856483,
"learning_rate": 8.764693200363897e-06,
"loss": 0.2956,
"step": 305
},
{
"epoch": 0.4587706146926537,
"grad_norm": 1.7345777302006005,
"learning_rate": 8.756933693657863e-06,
"loss": 0.2973,
"step": 306
},
{
"epoch": 0.46026986506746626,
"grad_norm": 1.5703940224862079,
"learning_rate": 8.749153350612774e-06,
"loss": 0.308,
"step": 307
},
{
"epoch": 0.4617691154422789,
"grad_norm": 1.404543016239454,
"learning_rate": 8.74135221437921e-06,
"loss": 0.2627,
"step": 308
},
{
"epoch": 0.46326836581709147,
"grad_norm": 1.622914683273527,
"learning_rate": 8.733530328223076e-06,
"loss": 0.3194,
"step": 309
},
{
"epoch": 0.46476761619190404,
"grad_norm": 1.5992326369836218,
"learning_rate": 8.725687735525347e-06,
"loss": 0.2734,
"step": 310
},
{
"epoch": 0.4662668665667166,
"grad_norm": 1.428179973398535,
"learning_rate": 8.71782447978185e-06,
"loss": 0.2712,
"step": 311
},
{
"epoch": 0.46776611694152925,
"grad_norm": 1.7414623479311544,
"learning_rate": 8.709940604603006e-06,
"loss": 0.3752,
"step": 312
},
{
"epoch": 0.46926536731634183,
"grad_norm": 1.5254762699797346,
"learning_rate": 8.702036153713594e-06,
"loss": 0.2906,
"step": 313
},
{
"epoch": 0.4707646176911544,
"grad_norm": 1.7397895016458929,
"learning_rate": 8.694111170952508e-06,
"loss": 0.2952,
"step": 314
},
{
"epoch": 0.47226386806596704,
"grad_norm": 1.6313154976101212,
"learning_rate": 8.686165700272513e-06,
"loss": 0.366,
"step": 315
},
{
"epoch": 0.4737631184407796,
"grad_norm": 1.4125903031749254,
"learning_rate": 8.678199785740003e-06,
"loss": 0.3001,
"step": 316
},
{
"epoch": 0.4752623688155922,
"grad_norm": 1.755982750732745,
"learning_rate": 8.670213471534759e-06,
"loss": 0.3552,
"step": 317
},
{
"epoch": 0.4767616191904048,
"grad_norm": 1.2975586714056746,
"learning_rate": 8.662206801949694e-06,
"loss": 0.2636,
"step": 318
},
{
"epoch": 0.4782608695652174,
"grad_norm": 1.479543914420989,
"learning_rate": 8.65417982139062e-06,
"loss": 0.2861,
"step": 319
},
{
"epoch": 0.47976011994003,
"grad_norm": 1.9072158128288146,
"learning_rate": 8.646132574375994e-06,
"loss": 0.3529,
"step": 320
},
{
"epoch": 0.48125937031484256,
"grad_norm": 1.6593484800640623,
"learning_rate": 8.638065105536669e-06,
"loss": 0.3585,
"step": 321
},
{
"epoch": 0.4827586206896552,
"grad_norm": 1.557791975939994,
"learning_rate": 8.629977459615655e-06,
"loss": 0.2912,
"step": 322
},
{
"epoch": 0.48425787106446777,
"grad_norm": 1.5749646653775289,
"learning_rate": 8.621869681467865e-06,
"loss": 0.3086,
"step": 323
},
{
"epoch": 0.48575712143928035,
"grad_norm": 1.3922529355839681,
"learning_rate": 8.613741816059867e-06,
"loss": 0.2526,
"step": 324
},
{
"epoch": 0.487256371814093,
"grad_norm": 1.6418433758391113,
"learning_rate": 8.605593908469635e-06,
"loss": 0.3063,
"step": 325
},
{
"epoch": 0.48875562218890556,
"grad_norm": 1.4903262726922777,
"learning_rate": 8.597426003886295e-06,
"loss": 0.2728,
"step": 326
},
{
"epoch": 0.49025487256371814,
"grad_norm": 1.540376386023962,
"learning_rate": 8.58923814760989e-06,
"loss": 0.3628,
"step": 327
},
{
"epoch": 0.4917541229385307,
"grad_norm": 1.6746744953148947,
"learning_rate": 8.581030385051105e-06,
"loss": 0.3481,
"step": 328
},
{
"epoch": 0.49325337331334335,
"grad_norm": 1.4618828442301055,
"learning_rate": 8.572802761731031e-06,
"loss": 0.3116,
"step": 329
},
{
"epoch": 0.4947526236881559,
"grad_norm": 1.61057521662318,
"learning_rate": 8.564555323280913e-06,
"loss": 0.3441,
"step": 330
},
{
"epoch": 0.4962518740629685,
"grad_norm": 1.5935367638144864,
"learning_rate": 8.556288115441887e-06,
"loss": 0.2965,
"step": 331
},
{
"epoch": 0.49775112443778113,
"grad_norm": 1.4319307113091793,
"learning_rate": 8.548001184064733e-06,
"loss": 0.3142,
"step": 332
},
{
"epoch": 0.4992503748125937,
"grad_norm": 1.445981529258563,
"learning_rate": 8.539694575109626e-06,
"loss": 0.2888,
"step": 333
},
{
"epoch": 0.5007496251874063,
"grad_norm": 1.602359221078496,
"learning_rate": 8.531368334645865e-06,
"loss": 0.293,
"step": 334
},
{
"epoch": 0.5022488755622189,
"grad_norm": 1.4353041375153546,
"learning_rate": 8.523022508851634e-06,
"loss": 0.3208,
"step": 335
},
{
"epoch": 0.5037481259370314,
"grad_norm": 1.5579714022068125,
"learning_rate": 8.514657144013738e-06,
"loss": 0.321,
"step": 336
},
{
"epoch": 0.5052473763118441,
"grad_norm": 1.5996183538119209,
"learning_rate": 8.506272286527346e-06,
"loss": 0.3876,
"step": 337
},
{
"epoch": 0.5067466266866567,
"grad_norm": 1.331308779665969,
"learning_rate": 8.497867982895741e-06,
"loss": 0.2726,
"step": 338
},
{
"epoch": 0.5082458770614693,
"grad_norm": 1.285540672848639,
"learning_rate": 8.489444279730046e-06,
"loss": 0.2651,
"step": 339
},
{
"epoch": 0.5097451274362819,
"grad_norm": 1.648005626003441,
"learning_rate": 8.481001223748986e-06,
"loss": 0.2765,
"step": 340
},
{
"epoch": 0.5112443778110944,
"grad_norm": 1.8337590942749775,
"learning_rate": 8.47253886177861e-06,
"loss": 0.3834,
"step": 341
},
{
"epoch": 0.512743628185907,
"grad_norm": 1.5746904364262109,
"learning_rate": 8.464057240752046e-06,
"loss": 0.3147,
"step": 342
},
{
"epoch": 0.5142428785607196,
"grad_norm": 1.5583080179143252,
"learning_rate": 8.455556407709235e-06,
"loss": 0.2502,
"step": 343
},
{
"epoch": 0.5157421289355323,
"grad_norm": 1.3784299657729973,
"learning_rate": 8.447036409796663e-06,
"loss": 0.3245,
"step": 344
},
{
"epoch": 0.5172413793103449,
"grad_norm": 1.421009503935526,
"learning_rate": 8.438497294267117e-06,
"loss": 0.3185,
"step": 345
},
{
"epoch": 0.5187406296851574,
"grad_norm": 1.734142097530356,
"learning_rate": 8.429939108479403e-06,
"loss": 0.4028,
"step": 346
},
{
"epoch": 0.52023988005997,
"grad_norm": 1.4283181015193642,
"learning_rate": 8.421361899898095e-06,
"loss": 0.3064,
"step": 347
},
{
"epoch": 0.5217391304347826,
"grad_norm": 1.48706713874812,
"learning_rate": 8.412765716093273e-06,
"loss": 0.2841,
"step": 348
},
{
"epoch": 0.5232383808095952,
"grad_norm": 1.5120205939898492,
"learning_rate": 8.404150604740248e-06,
"loss": 0.3197,
"step": 349
},
{
"epoch": 0.5247376311844077,
"grad_norm": 1.5731350530900636,
"learning_rate": 8.395516613619315e-06,
"loss": 0.305,
"step": 350
},
{
"epoch": 0.5262368815592204,
"grad_norm": 1.4591781180792678,
"learning_rate": 8.386863790615472e-06,
"loss": 0.3305,
"step": 351
},
{
"epoch": 0.527736131934033,
"grad_norm": 1.5988860912943819,
"learning_rate": 8.378192183718158e-06,
"loss": 0.3358,
"step": 352
},
{
"epoch": 0.5292353823088456,
"grad_norm": 1.690987090893082,
"learning_rate": 8.369501841021e-06,
"loss": 0.3412,
"step": 353
},
{
"epoch": 0.5307346326836582,
"grad_norm": 1.5892248038221097,
"learning_rate": 8.360792810721522e-06,
"loss": 0.2828,
"step": 354
},
{
"epoch": 0.5322338830584707,
"grad_norm": 1.5179989556837041,
"learning_rate": 8.352065141120902e-06,
"loss": 0.3209,
"step": 355
},
{
"epoch": 0.5337331334332833,
"grad_norm": 1.5600522653768132,
"learning_rate": 8.343318880623688e-06,
"loss": 0.2921,
"step": 356
},
{
"epoch": 0.5352323838080959,
"grad_norm": 1.5555612059413912,
"learning_rate": 8.334554077737535e-06,
"loss": 0.3502,
"step": 357
},
{
"epoch": 0.5367316341829086,
"grad_norm": 1.3576244747622102,
"learning_rate": 8.325770781072939e-06,
"loss": 0.2899,
"step": 358
},
{
"epoch": 0.5382308845577212,
"grad_norm": 1.255414514400548,
"learning_rate": 8.316969039342963e-06,
"loss": 0.301,
"step": 359
},
{
"epoch": 0.5397301349325337,
"grad_norm": 1.4403501035341664,
"learning_rate": 8.30814890136297e-06,
"loss": 0.2321,
"step": 360
},
{
"epoch": 0.5412293853073463,
"grad_norm": 2.0042523749431047,
"learning_rate": 8.299310416050345e-06,
"loss": 0.3766,
"step": 361
},
{
"epoch": 0.5427286356821589,
"grad_norm": 1.329044305552415,
"learning_rate": 8.290453632424236e-06,
"loss": 0.246,
"step": 362
},
{
"epoch": 0.5442278860569715,
"grad_norm": 1.8038806480964888,
"learning_rate": 8.281578599605269e-06,
"loss": 0.3285,
"step": 363
},
{
"epoch": 0.545727136431784,
"grad_norm": 1.6972593164495602,
"learning_rate": 8.272685366815287e-06,
"loss": 0.3985,
"step": 364
},
{
"epoch": 0.5472263868065967,
"grad_norm": 1.3418317537268136,
"learning_rate": 8.26377398337707e-06,
"loss": 0.3338,
"step": 365
},
{
"epoch": 0.5487256371814093,
"grad_norm": 1.5696789006175893,
"learning_rate": 8.254844498714063e-06,
"loss": 0.2931,
"step": 366
},
{
"epoch": 0.5502248875562219,
"grad_norm": 1.4863325632462137,
"learning_rate": 8.2458969623501e-06,
"loss": 0.3632,
"step": 367
},
{
"epoch": 0.5517241379310345,
"grad_norm": 1.4927122577519016,
"learning_rate": 8.23693142390914e-06,
"loss": 0.3526,
"step": 368
},
{
"epoch": 0.553223388305847,
"grad_norm": 1.4142612730492767,
"learning_rate": 8.227947933114971e-06,
"loss": 0.2575,
"step": 369
},
{
"epoch": 0.5547226386806596,
"grad_norm": 1.526469855561163,
"learning_rate": 8.218946539790957e-06,
"loss": 0.3258,
"step": 370
},
{
"epoch": 0.5562218890554723,
"grad_norm": 1.3984879591660238,
"learning_rate": 8.209927293859746e-06,
"loss": 0.303,
"step": 371
},
{
"epoch": 0.5577211394302849,
"grad_norm": 1.6745387934507217,
"learning_rate": 8.200890245342999e-06,
"loss": 0.3799,
"step": 372
},
{
"epoch": 0.5592203898050975,
"grad_norm": 1.56228468138885,
"learning_rate": 8.191835444361113e-06,
"loss": 0.3917,
"step": 373
},
{
"epoch": 0.56071964017991,
"grad_norm": 1.3202553723061632,
"learning_rate": 8.182762941132944e-06,
"loss": 0.2632,
"step": 374
},
{
"epoch": 0.5622188905547226,
"grad_norm": 1.4285299922962245,
"learning_rate": 8.173672785975522e-06,
"loss": 0.3207,
"step": 375
},
{
"epoch": 0.5637181409295352,
"grad_norm": 1.7706320948302563,
"learning_rate": 8.16456502930378e-06,
"loss": 0.411,
"step": 376
},
{
"epoch": 0.5652173913043478,
"grad_norm": 1.5555404146846652,
"learning_rate": 8.155439721630265e-06,
"loss": 0.3402,
"step": 377
},
{
"epoch": 0.5667166416791605,
"grad_norm": 1.280491820060774,
"learning_rate": 8.146296913564872e-06,
"loss": 0.2763,
"step": 378
},
{
"epoch": 0.568215892053973,
"grad_norm": 1.498816208536415,
"learning_rate": 8.13713665581455e-06,
"loss": 0.2841,
"step": 379
},
{
"epoch": 0.5697151424287856,
"grad_norm": 1.3741949197493073,
"learning_rate": 8.127958999183027e-06,
"loss": 0.3014,
"step": 380
},
{
"epoch": 0.5712143928035982,
"grad_norm": 1.2879534077401542,
"learning_rate": 8.118763994570528e-06,
"loss": 0.3213,
"step": 381
},
{
"epoch": 0.5727136431784108,
"grad_norm": 1.7415653668034985,
"learning_rate": 8.109551692973487e-06,
"loss": 0.2967,
"step": 382
},
{
"epoch": 0.5742128935532234,
"grad_norm": 1.3504330250600425,
"learning_rate": 8.100322145484275e-06,
"loss": 0.3172,
"step": 383
},
{
"epoch": 0.5757121439280359,
"grad_norm": 1.4398060360351141,
"learning_rate": 8.091075403290905e-06,
"loss": 0.3221,
"step": 384
},
{
"epoch": 0.5772113943028486,
"grad_norm": 1.4685973288174197,
"learning_rate": 8.081811517676759e-06,
"loss": 0.3036,
"step": 385
},
{
"epoch": 0.5787106446776612,
"grad_norm": 1.3757946392665268,
"learning_rate": 8.072530540020294e-06,
"loss": 0.3174,
"step": 386
},
{
"epoch": 0.5802098950524738,
"grad_norm": 1.3207011248499667,
"learning_rate": 8.063232521794762e-06,
"loss": 0.2801,
"step": 387
},
{
"epoch": 0.5817091454272864,
"grad_norm": 1.1766688774818337,
"learning_rate": 8.053917514567927e-06,
"loss": 0.241,
"step": 388
},
{
"epoch": 0.5832083958020989,
"grad_norm": 1.3126653214263113,
"learning_rate": 8.04458557000177e-06,
"loss": 0.2809,
"step": 389
},
{
"epoch": 0.5847076461769115,
"grad_norm": 1.6207249995016972,
"learning_rate": 8.035236739852214e-06,
"loss": 0.3034,
"step": 390
},
{
"epoch": 0.5862068965517241,
"grad_norm": 1.8716872118030787,
"learning_rate": 8.025871075968828e-06,
"loss": 0.3139,
"step": 391
},
{
"epoch": 0.5877061469265368,
"grad_norm": 1.3766598114110888,
"learning_rate": 8.016488630294539e-06,
"loss": 0.2851,
"step": 392
},
{
"epoch": 0.5892053973013494,
"grad_norm": 1.437525290716419,
"learning_rate": 8.007089454865358e-06,
"loss": 0.3209,
"step": 393
},
{
"epoch": 0.5907046476761619,
"grad_norm": 1.45491223433416,
"learning_rate": 7.997673601810071e-06,
"loss": 0.267,
"step": 394
},
{
"epoch": 0.5922038980509745,
"grad_norm": 1.144356936174265,
"learning_rate": 7.988241123349965e-06,
"loss": 0.2979,
"step": 395
},
{
"epoch": 0.5937031484257871,
"grad_norm": 1.6160780957452199,
"learning_rate": 7.97879207179853e-06,
"loss": 0.2878,
"step": 396
},
{
"epoch": 0.5952023988005997,
"grad_norm": 1.4698046543076704,
"learning_rate": 7.969326499561173e-06,
"loss": 0.2815,
"step": 397
},
{
"epoch": 0.5967016491754122,
"grad_norm": 1.5580121554949924,
"learning_rate": 7.95984445913493e-06,
"loss": 0.3351,
"step": 398
},
{
"epoch": 0.5982008995502249,
"grad_norm": 1.2610592076882203,
"learning_rate": 7.950346003108167e-06,
"loss": 0.258,
"step": 399
},
{
"epoch": 0.5997001499250375,
"grad_norm": 1.280154159142727,
"learning_rate": 7.940831184160294e-06,
"loss": 0.2849,
"step": 400
},
{
"epoch": 0.5997001499250375,
"eval_loss": 0.3021397590637207,
"eval_runtime": 9.5189,
"eval_samples_per_second": 5.673,
"eval_steps_per_second": 1.471,
"step": 400
},
{
"epoch": 0.6011994002998501,
"grad_norm": 1.3919665388781326,
"learning_rate": 7.93130005506147e-06,
"loss": 0.3171,
"step": 401
},
{
"epoch": 0.6026986506746627,
"grad_norm": 1.217918218721182,
"learning_rate": 7.921752668672316e-06,
"loss": 0.2821,
"step": 402
},
{
"epoch": 0.6041979010494752,
"grad_norm": 1.4425838660870236,
"learning_rate": 7.912189077943613e-06,
"loss": 0.2888,
"step": 403
},
{
"epoch": 0.6056971514242878,
"grad_norm": 1.4996475538548084,
"learning_rate": 7.902609335916015e-06,
"loss": 0.2627,
"step": 404
},
{
"epoch": 0.6071964017991005,
"grad_norm": 1.4619821265759678,
"learning_rate": 7.893013495719752e-06,
"loss": 0.302,
"step": 405
},
{
"epoch": 0.6086956521739131,
"grad_norm": 1.529852377257847,
"learning_rate": 7.883401610574338e-06,
"loss": 0.3041,
"step": 406
},
{
"epoch": 0.6101949025487257,
"grad_norm": 1.6245528888965435,
"learning_rate": 7.873773733788268e-06,
"loss": 0.3132,
"step": 407
},
{
"epoch": 0.6116941529235382,
"grad_norm": 1.592388100708721,
"learning_rate": 7.864129918758738e-06,
"loss": 0.3218,
"step": 408
},
{
"epoch": 0.6131934032983508,
"grad_norm": 1.2782270070716457,
"learning_rate": 7.854470218971333e-06,
"loss": 0.3132,
"step": 409
},
{
"epoch": 0.6146926536731634,
"grad_norm": 1.4920393997659043,
"learning_rate": 7.844794687999737e-06,
"loss": 0.3011,
"step": 410
},
{
"epoch": 0.616191904047976,
"grad_norm": 1.7736914495043172,
"learning_rate": 7.835103379505433e-06,
"loss": 0.3163,
"step": 411
},
{
"epoch": 0.6176911544227887,
"grad_norm": 1.7683774569170425,
"learning_rate": 7.825396347237413e-06,
"loss": 0.3077,
"step": 412
},
{
"epoch": 0.6191904047976012,
"grad_norm": 1.4797183745953193,
"learning_rate": 7.815673645031871e-06,
"loss": 0.3246,
"step": 413
},
{
"epoch": 0.6206896551724138,
"grad_norm": 1.4362048583158942,
"learning_rate": 7.805935326811913e-06,
"loss": 0.3035,
"step": 414
},
{
"epoch": 0.6221889055472264,
"grad_norm": 1.5423426053687976,
"learning_rate": 7.796181446587244e-06,
"loss": 0.2674,
"step": 415
},
{
"epoch": 0.623688155922039,
"grad_norm": 1.4145697008017475,
"learning_rate": 7.786412058453886e-06,
"loss": 0.2851,
"step": 416
},
{
"epoch": 0.6251874062968515,
"grad_norm": 1.4263423096837133,
"learning_rate": 7.776627216593863e-06,
"loss": 0.2572,
"step": 417
},
{
"epoch": 0.6266866566716641,
"grad_norm": 1.586549287920147,
"learning_rate": 7.766826975274916e-06,
"loss": 0.2712,
"step": 418
},
{
"epoch": 0.6281859070464768,
"grad_norm": 1.5131788482439936,
"learning_rate": 7.75701138885018e-06,
"loss": 0.2992,
"step": 419
},
{
"epoch": 0.6296851574212894,
"grad_norm": 1.5020750976431931,
"learning_rate": 7.747180511757908e-06,
"loss": 0.3074,
"step": 420
},
{
"epoch": 0.631184407796102,
"grad_norm": 1.3538347735977267,
"learning_rate": 7.737334398521149e-06,
"loss": 0.263,
"step": 421
},
{
"epoch": 0.6326836581709145,
"grad_norm": 1.514413986867279,
"learning_rate": 7.727473103747456e-06,
"loss": 0.3495,
"step": 422
},
{
"epoch": 0.6341829085457271,
"grad_norm": 1.4612722169079506,
"learning_rate": 7.717596682128578e-06,
"loss": 0.2521,
"step": 423
},
{
"epoch": 0.6356821589205397,
"grad_norm": 1.4649249453385167,
"learning_rate": 7.707705188440165e-06,
"loss": 0.2902,
"step": 424
},
{
"epoch": 0.6371814092953523,
"grad_norm": 1.5852062661832558,
"learning_rate": 7.697798677541448e-06,
"loss": 0.3088,
"step": 425
},
{
"epoch": 0.638680659670165,
"grad_norm": 1.3241949061805072,
"learning_rate": 7.687877204374957e-06,
"loss": 0.2478,
"step": 426
},
{
"epoch": 0.6401799100449775,
"grad_norm": 1.4030774313449836,
"learning_rate": 7.677940823966196e-06,
"loss": 0.2558,
"step": 427
},
{
"epoch": 0.6416791604197901,
"grad_norm": 1.402885148784031,
"learning_rate": 7.667989591423349e-06,
"loss": 0.3037,
"step": 428
},
{
"epoch": 0.6431784107946027,
"grad_norm": 1.277487083138602,
"learning_rate": 7.658023561936966e-06,
"loss": 0.2346,
"step": 429
},
{
"epoch": 0.6446776611694153,
"grad_norm": 1.3581505687018312,
"learning_rate": 7.648042790779677e-06,
"loss": 0.293,
"step": 430
},
{
"epoch": 0.6461769115442278,
"grad_norm": 1.5221074822476175,
"learning_rate": 7.638047333305853e-06,
"loss": 0.3228,
"step": 431
},
{
"epoch": 0.6476761619190404,
"grad_norm": 1.4895620088229964,
"learning_rate": 7.628037244951328e-06,
"loss": 0.3148,
"step": 432
},
{
"epoch": 0.6491754122938531,
"grad_norm": 1.514290497632156,
"learning_rate": 7.618012581233076e-06,
"loss": 0.3167,
"step": 433
},
{
"epoch": 0.6506746626686657,
"grad_norm": 1.3716765759657792,
"learning_rate": 7.607973397748909e-06,
"loss": 0.3057,
"step": 434
},
{
"epoch": 0.6521739130434783,
"grad_norm": 1.4837843327419138,
"learning_rate": 7.597919750177168e-06,
"loss": 0.2974,
"step": 435
},
{
"epoch": 0.6536731634182908,
"grad_norm": 1.5261849742576514,
"learning_rate": 7.587851694276412e-06,
"loss": 0.2834,
"step": 436
},
{
"epoch": 0.6551724137931034,
"grad_norm": 1.47832766014606,
"learning_rate": 7.57776928588511e-06,
"loss": 0.2714,
"step": 437
},
{
"epoch": 0.656671664167916,
"grad_norm": 1.2933753299940371,
"learning_rate": 7.56767258092133e-06,
"loss": 0.3007,
"step": 438
},
{
"epoch": 0.6581709145427287,
"grad_norm": 1.5864089772861663,
"learning_rate": 7.557561635382433e-06,
"loss": 0.3543,
"step": 439
},
{
"epoch": 0.6596701649175413,
"grad_norm": 1.2596054376286927,
"learning_rate": 7.54743650534476e-06,
"loss": 0.2657,
"step": 440
},
{
"epoch": 0.6611694152923538,
"grad_norm": 1.4915827024861525,
"learning_rate": 7.537297246963316e-06,
"loss": 0.3082,
"step": 441
},
{
"epoch": 0.6626686656671664,
"grad_norm": 1.447635534551508,
"learning_rate": 7.5271439164714695e-06,
"loss": 0.3202,
"step": 442
},
{
"epoch": 0.664167916041979,
"grad_norm": 1.206525246287725,
"learning_rate": 7.5169765701806295e-06,
"loss": 0.2689,
"step": 443
},
{
"epoch": 0.6656671664167916,
"grad_norm": 1.521284178006273,
"learning_rate": 7.506795264479941e-06,
"loss": 0.2897,
"step": 444
},
{
"epoch": 0.6671664167916042,
"grad_norm": 1.4116064152432382,
"learning_rate": 7.4966000558359675e-06,
"loss": 0.2929,
"step": 445
},
{
"epoch": 0.6686656671664168,
"grad_norm": 1.6492116988043684,
"learning_rate": 7.486391000792379e-06,
"loss": 0.3485,
"step": 446
},
{
"epoch": 0.6701649175412294,
"grad_norm": 1.7455678286882141,
"learning_rate": 7.476168155969643e-06,
"loss": 0.4197,
"step": 447
},
{
"epoch": 0.671664167916042,
"grad_norm": 1.5935825968847936,
"learning_rate": 7.465931578064703e-06,
"loss": 0.2765,
"step": 448
},
{
"epoch": 0.6731634182908546,
"grad_norm": 1.3190269078682864,
"learning_rate": 7.455681323850669e-06,
"loss": 0.2788,
"step": 449
},
{
"epoch": 0.6746626686656672,
"grad_norm": 1.3649129605274712,
"learning_rate": 7.4454174501765e-06,
"loss": 0.3065,
"step": 450
},
{
"epoch": 0.6761619190404797,
"grad_norm": 1.308593989007283,
"learning_rate": 7.4351400139666894e-06,
"loss": 0.2694,
"step": 451
},
{
"epoch": 0.6776611694152923,
"grad_norm": 1.2894750680147766,
"learning_rate": 7.424849072220953e-06,
"loss": 0.3125,
"step": 452
},
{
"epoch": 0.679160419790105,
"grad_norm": 1.4847915599618102,
"learning_rate": 7.414544682013907e-06,
"loss": 0.301,
"step": 453
},
{
"epoch": 0.6806596701649176,
"grad_norm": 1.5232019125166283,
"learning_rate": 7.404226900494753e-06,
"loss": 0.3267,
"step": 454
},
{
"epoch": 0.6821589205397302,
"grad_norm": 1.2345785992963527,
"learning_rate": 7.3938957848869684e-06,
"loss": 0.2745,
"step": 455
},
{
"epoch": 0.6836581709145427,
"grad_norm": 1.635858249949889,
"learning_rate": 7.3835513924879755e-06,
"loss": 0.3125,
"step": 456
},
{
"epoch": 0.6851574212893553,
"grad_norm": 1.149820377473072,
"learning_rate": 7.373193780668835e-06,
"loss": 0.2396,
"step": 457
},
{
"epoch": 0.6866566716641679,
"grad_norm": 1.3222898367566278,
"learning_rate": 7.36282300687392e-06,
"loss": 0.2946,
"step": 458
},
{
"epoch": 0.6881559220389805,
"grad_norm": 1.7971708473069352,
"learning_rate": 7.35243912862061e-06,
"loss": 0.3595,
"step": 459
},
{
"epoch": 0.6896551724137931,
"grad_norm": 1.5140137944873706,
"learning_rate": 7.342042203498952e-06,
"loss": 0.3277,
"step": 460
},
{
"epoch": 0.6911544227886057,
"grad_norm": 1.695383595122999,
"learning_rate": 7.33163228917136e-06,
"loss": 0.3617,
"step": 461
},
{
"epoch": 0.6926536731634183,
"grad_norm": 1.296170215239378,
"learning_rate": 7.321209443372284e-06,
"loss": 0.2577,
"step": 462
},
{
"epoch": 0.6941529235382309,
"grad_norm": 1.5669072802310569,
"learning_rate": 7.310773723907895e-06,
"loss": 0.3807,
"step": 463
},
{
"epoch": 0.6956521739130435,
"grad_norm": 1.3689687819823577,
"learning_rate": 7.300325188655762e-06,
"loss": 0.2598,
"step": 464
},
{
"epoch": 0.697151424287856,
"grad_norm": 1.6055006193320565,
"learning_rate": 7.289863895564531e-06,
"loss": 0.3482,
"step": 465
},
{
"epoch": 0.6986506746626686,
"grad_norm": 1.4514949398414718,
"learning_rate": 7.279389902653606e-06,
"loss": 0.2931,
"step": 466
},
{
"epoch": 0.7001499250374813,
"grad_norm": 1.7002732718419034,
"learning_rate": 7.268903268012823e-06,
"loss": 0.3401,
"step": 467
},
{
"epoch": 0.7016491754122939,
"grad_norm": 1.1984173265549762,
"learning_rate": 7.258404049802135e-06,
"loss": 0.2287,
"step": 468
},
{
"epoch": 0.7031484257871065,
"grad_norm": 1.140211799491912,
"learning_rate": 7.247892306251276e-06,
"loss": 0.226,
"step": 469
},
{
"epoch": 0.704647676161919,
"grad_norm": 1.3027451409213062,
"learning_rate": 7.237368095659459e-06,
"loss": 0.3169,
"step": 470
},
{
"epoch": 0.7061469265367316,
"grad_norm": 1.6413347599296277,
"learning_rate": 7.226831476395028e-06,
"loss": 0.3011,
"step": 471
},
{
"epoch": 0.7076461769115442,
"grad_norm": 1.6722238750016507,
"learning_rate": 7.216282506895155e-06,
"loss": 0.2884,
"step": 472
},
{
"epoch": 0.7091454272863568,
"grad_norm": 1.3820652066622765,
"learning_rate": 7.2057212456655055e-06,
"loss": 0.3051,
"step": 473
},
{
"epoch": 0.7106446776611695,
"grad_norm": 1.4627147047856914,
"learning_rate": 7.195147751279915e-06,
"loss": 0.2925,
"step": 474
},
{
"epoch": 0.712143928035982,
"grad_norm": 1.5615572592798332,
"learning_rate": 7.184562082380069e-06,
"loss": 0.3061,
"step": 475
},
{
"epoch": 0.7136431784107946,
"grad_norm": 1.7127142065683358,
"learning_rate": 7.173964297675168e-06,
"loss": 0.344,
"step": 476
},
{
"epoch": 0.7151424287856072,
"grad_norm": 1.5486907588716836,
"learning_rate": 7.163354455941614e-06,
"loss": 0.3265,
"step": 477
},
{
"epoch": 0.7166416791604198,
"grad_norm": 1.4030585005720235,
"learning_rate": 7.152732616022675e-06,
"loss": 0.2665,
"step": 478
},
{
"epoch": 0.7181409295352323,
"grad_norm": 1.3322057839222532,
"learning_rate": 7.142098836828162e-06,
"loss": 0.3117,
"step": 479
},
{
"epoch": 0.719640179910045,
"grad_norm": 1.3975504878625638,
"learning_rate": 7.131453177334103e-06,
"loss": 0.3069,
"step": 480
},
{
"epoch": 0.7211394302848576,
"grad_norm": 1.0945088603081936,
"learning_rate": 7.120795696582419e-06,
"loss": 0.2516,
"step": 481
},
{
"epoch": 0.7226386806596702,
"grad_norm": 1.4290632578017513,
"learning_rate": 7.1101264536805885e-06,
"loss": 0.2829,
"step": 482
},
{
"epoch": 0.7241379310344828,
"grad_norm": 1.4243890988280488,
"learning_rate": 7.099445507801324e-06,
"loss": 0.281,
"step": 483
},
{
"epoch": 0.7256371814092953,
"grad_norm": 1.4278402465378144,
"learning_rate": 7.088752918182247e-06,
"loss": 0.2676,
"step": 484
},
{
"epoch": 0.7271364317841079,
"grad_norm": 1.5069524803063328,
"learning_rate": 7.078048744125553e-06,
"loss": 0.3263,
"step": 485
},
{
"epoch": 0.7286356821589205,
"grad_norm": 1.1209588755097866,
"learning_rate": 7.067333044997689e-06,
"loss": 0.2555,
"step": 486
},
{
"epoch": 0.7301349325337332,
"grad_norm": 1.4233085489601176,
"learning_rate": 7.0566058802290196e-06,
"loss": 0.3053,
"step": 487
},
{
"epoch": 0.7316341829085458,
"grad_norm": 1.3003998702719686,
"learning_rate": 7.045867309313499e-06,
"loss": 0.3077,
"step": 488
},
{
"epoch": 0.7331334332833583,
"grad_norm": 1.371637304171436,
"learning_rate": 7.035117391808341e-06,
"loss": 0.2882,
"step": 489
},
{
"epoch": 0.7346326836581709,
"grad_norm": 1.3700945109307232,
"learning_rate": 7.024356187333692e-06,
"loss": 0.3535,
"step": 490
},
{
"epoch": 0.7361319340329835,
"grad_norm": 1.372970950040628,
"learning_rate": 7.01358375557229e-06,
"loss": 0.3184,
"step": 491
},
{
"epoch": 0.7376311844077961,
"grad_norm": 1.3825121720318863,
"learning_rate": 7.0028001562691475e-06,
"loss": 0.2722,
"step": 492
},
{
"epoch": 0.7391304347826086,
"grad_norm": 1.3013775517397221,
"learning_rate": 6.9920054492312086e-06,
"loss": 0.3287,
"step": 493
},
{
"epoch": 0.7406296851574213,
"grad_norm": 1.4737084227604176,
"learning_rate": 6.981199694327024e-06,
"loss": 0.3094,
"step": 494
},
{
"epoch": 0.7421289355322339,
"grad_norm": 1.3101411746781326,
"learning_rate": 6.97038295148642e-06,
"loss": 0.2839,
"step": 495
},
{
"epoch": 0.7436281859070465,
"grad_norm": 1.4892593890064303,
"learning_rate": 6.959555280700162e-06,
"loss": 0.2964,
"step": 496
},
{
"epoch": 0.7451274362818591,
"grad_norm": 1.7096190584184843,
"learning_rate": 6.948716742019616e-06,
"loss": 0.294,
"step": 497
},
{
"epoch": 0.7466266866566716,
"grad_norm": 1.3979921629169787,
"learning_rate": 6.937867395556428e-06,
"loss": 0.3193,
"step": 498
},
{
"epoch": 0.7481259370314842,
"grad_norm": 1.44777450491065,
"learning_rate": 6.927007301482187e-06,
"loss": 0.2905,
"step": 499
},
{
"epoch": 0.7496251874062968,
"grad_norm": 1.271551321930749,
"learning_rate": 6.916136520028087e-06,
"loss": 0.297,
"step": 500
},
{
"epoch": 0.7511244377811095,
"grad_norm": 1.5139383519838707,
"learning_rate": 6.905255111484592e-06,
"loss": 0.2959,
"step": 501
},
{
"epoch": 0.7526236881559221,
"grad_norm": 1.6128675870437148,
"learning_rate": 6.894363136201114e-06,
"loss": 0.3524,
"step": 502
},
{
"epoch": 0.7541229385307346,
"grad_norm": 1.4424070702121157,
"learning_rate": 6.88346065458566e-06,
"loss": 0.3102,
"step": 503
},
{
"epoch": 0.7556221889055472,
"grad_norm": 1.3671962301245493,
"learning_rate": 6.8725477271045085e-06,
"loss": 0.3026,
"step": 504
},
{
"epoch": 0.7571214392803598,
"grad_norm": 1.442281151937481,
"learning_rate": 6.861624414281875e-06,
"loss": 0.2777,
"step": 505
},
{
"epoch": 0.7586206896551724,
"grad_norm": 1.3749554454658155,
"learning_rate": 6.850690776699574e-06,
"loss": 0.2678,
"step": 506
},
{
"epoch": 0.760119940029985,
"grad_norm": 1.4900828297443907,
"learning_rate": 6.8397468749966735e-06,
"loss": 0.3366,
"step": 507
},
{
"epoch": 0.7616191904047976,
"grad_norm": 1.4659412454705263,
"learning_rate": 6.8287927698691745e-06,
"loss": 0.318,
"step": 508
},
{
"epoch": 0.7631184407796102,
"grad_norm": 1.3001117219908083,
"learning_rate": 6.8178285220696686e-06,
"loss": 0.315,
"step": 509
},
{
"epoch": 0.7646176911544228,
"grad_norm": 1.2959059727140845,
"learning_rate": 6.806854192406995e-06,
"loss": 0.2421,
"step": 510
},
{
"epoch": 0.7661169415292354,
"grad_norm": 1.5826201560626563,
"learning_rate": 6.795869841745912e-06,
"loss": 0.3146,
"step": 511
},
{
"epoch": 0.767616191904048,
"grad_norm": 1.4578325207942953,
"learning_rate": 6.784875531006751e-06,
"loss": 0.3353,
"step": 512
},
{
"epoch": 0.7691154422788605,
"grad_norm": 1.161682568121232,
"learning_rate": 6.7738713211650885e-06,
"loss": 0.2926,
"step": 513
},
{
"epoch": 0.7706146926536732,
"grad_norm": 1.5305535208266787,
"learning_rate": 6.762857273251396e-06,
"loss": 0.3128,
"step": 514
},
{
"epoch": 0.7721139430284858,
"grad_norm": 1.7063210636875437,
"learning_rate": 6.751833448350713e-06,
"loss": 0.2993,
"step": 515
},
{
"epoch": 0.7736131934032984,
"grad_norm": 1.6456135292610181,
"learning_rate": 6.740799907602302e-06,
"loss": 0.3019,
"step": 516
},
{
"epoch": 0.775112443778111,
"grad_norm": 1.2426157748268456,
"learning_rate": 6.729756712199309e-06,
"loss": 0.2824,
"step": 517
},
{
"epoch": 0.7766116941529235,
"grad_norm": 1.4837539502622794,
"learning_rate": 6.718703923388427e-06,
"loss": 0.2434,
"step": 518
},
{
"epoch": 0.7781109445277361,
"grad_norm": 1.3434614613743725,
"learning_rate": 6.707641602469554e-06,
"loss": 0.2599,
"step": 519
},
{
"epoch": 0.7796101949025487,
"grad_norm": 1.5499562443429653,
"learning_rate": 6.696569810795455e-06,
"loss": 0.3173,
"step": 520
},
{
"epoch": 0.7811094452773614,
"grad_norm": 1.3861012563538573,
"learning_rate": 6.685488609771422e-06,
"loss": 0.2949,
"step": 521
},
{
"epoch": 0.782608695652174,
"grad_norm": 1.6224606096357699,
"learning_rate": 6.674398060854931e-06,
"loss": 0.3209,
"step": 522
},
{
"epoch": 0.7841079460269865,
"grad_norm": 1.3855377694609932,
"learning_rate": 6.6632982255553004e-06,
"loss": 0.2779,
"step": 523
},
{
"epoch": 0.7856071964017991,
"grad_norm": 1.6121761396352565,
"learning_rate": 6.652189165433356e-06,
"loss": 0.3242,
"step": 524
},
{
"epoch": 0.7871064467766117,
"grad_norm": 1.2201563254362011,
"learning_rate": 6.64107094210108e-06,
"loss": 0.2574,
"step": 525
},
{
"epoch": 0.7886056971514243,
"grad_norm": 1.5837106620290757,
"learning_rate": 6.62994361722128e-06,
"loss": 0.3597,
"step": 526
},
{
"epoch": 0.7901049475262368,
"grad_norm": 1.3080007300343965,
"learning_rate": 6.618807252507238e-06,
"loss": 0.2728,
"step": 527
},
{
"epoch": 0.7916041979010495,
"grad_norm": 1.7207174990749512,
"learning_rate": 6.6076619097223735e-06,
"loss": 0.3896,
"step": 528
},
{
"epoch": 0.7931034482758621,
"grad_norm": 1.8410214396008497,
"learning_rate": 6.5965076506799e-06,
"loss": 0.332,
"step": 529
},
{
"epoch": 0.7946026986506747,
"grad_norm": 1.5709803889468719,
"learning_rate": 6.5853445372424805e-06,
"loss": 0.3002,
"step": 530
},
{
"epoch": 0.7961019490254873,
"grad_norm": 1.6453166169425513,
"learning_rate": 6.574172631321885e-06,
"loss": 0.3038,
"step": 531
},
{
"epoch": 0.7976011994002998,
"grad_norm": 1.6454944309779433,
"learning_rate": 6.562991994878649e-06,
"loss": 0.3268,
"step": 532
},
{
"epoch": 0.7991004497751124,
"grad_norm": 1.568436292974634,
"learning_rate": 6.551802689921726e-06,
"loss": 0.3294,
"step": 533
},
{
"epoch": 0.800599700149925,
"grad_norm": 1.228856484817089,
"learning_rate": 6.5406047785081485e-06,
"loss": 0.2951,
"step": 534
},
{
"epoch": 0.8020989505247377,
"grad_norm": 1.150307761731132,
"learning_rate": 6.529398322742677e-06,
"loss": 0.2049,
"step": 535
},
{
"epoch": 0.8035982008995503,
"grad_norm": 1.2687951906666617,
"learning_rate": 6.518183384777468e-06,
"loss": 0.2396,
"step": 536
},
{
"epoch": 0.8050974512743628,
"grad_norm": 1.5860720753499649,
"learning_rate": 6.506960026811712e-06,
"loss": 0.3408,
"step": 537
},
{
"epoch": 0.8065967016491754,
"grad_norm": 1.400324377807205,
"learning_rate": 6.495728311091303e-06,
"loss": 0.2507,
"step": 538
},
{
"epoch": 0.808095952023988,
"grad_norm": 1.3407564762956719,
"learning_rate": 6.484488299908487e-06,
"loss": 0.2526,
"step": 539
},
{
"epoch": 0.8095952023988006,
"grad_norm": 1.694971638513342,
"learning_rate": 6.473240055601517e-06,
"loss": 0.2925,
"step": 540
},
{
"epoch": 0.8110944527736131,
"grad_norm": 1.3051634848999276,
"learning_rate": 6.46198364055431e-06,
"loss": 0.3198,
"step": 541
},
{
"epoch": 0.8125937031484258,
"grad_norm": 1.4209834742780914,
"learning_rate": 6.450719117196094e-06,
"loss": 0.2841,
"step": 542
},
{
"epoch": 0.8140929535232384,
"grad_norm": 1.5456807832456958,
"learning_rate": 6.439446548001069e-06,
"loss": 0.2894,
"step": 543
},
{
"epoch": 0.815592203898051,
"grad_norm": 1.6970824843923287,
"learning_rate": 6.4281659954880605e-06,
"loss": 0.3286,
"step": 544
},
{
"epoch": 0.8170914542728636,
"grad_norm": 1.5394537765295597,
"learning_rate": 6.416877522220167e-06,
"loss": 0.319,
"step": 545
},
{
"epoch": 0.8185907046476761,
"grad_norm": 1.5196056725942917,
"learning_rate": 6.405581190804418e-06,
"loss": 0.3121,
"step": 546
},
{
"epoch": 0.8200899550224887,
"grad_norm": 1.538525170169423,
"learning_rate": 6.394277063891422e-06,
"loss": 0.2982,
"step": 547
},
{
"epoch": 0.8215892053973014,
"grad_norm": 1.420879269740161,
"learning_rate": 6.382965204175027e-06,
"loss": 0.356,
"step": 548
},
{
"epoch": 0.823088455772114,
"grad_norm": 1.3803279644484636,
"learning_rate": 6.371645674391967e-06,
"loss": 0.2689,
"step": 549
},
{
"epoch": 0.8245877061469266,
"grad_norm": 1.5390146778775227,
"learning_rate": 6.3603185373215105e-06,
"loss": 0.2777,
"step": 550
},
{
"epoch": 0.8260869565217391,
"grad_norm": 1.2124994140317764,
"learning_rate": 6.348983855785122e-06,
"loss": 0.2975,
"step": 551
},
{
"epoch": 0.8275862068965517,
"grad_norm": 1.347666739407509,
"learning_rate": 6.337641692646106e-06,
"loss": 0.2931,
"step": 552
},
{
"epoch": 0.8290854572713643,
"grad_norm": 1.0316649456573812,
"learning_rate": 6.326292110809258e-06,
"loss": 0.2591,
"step": 553
},
{
"epoch": 0.8305847076461769,
"grad_norm": 1.1793130273689618,
"learning_rate": 6.314935173220524e-06,
"loss": 0.2472,
"step": 554
},
{
"epoch": 0.8320839580209896,
"grad_norm": 1.3306237638358906,
"learning_rate": 6.303570942866643e-06,
"loss": 0.3037,
"step": 555
},
{
"epoch": 0.8335832083958021,
"grad_norm": 1.2939098473779578,
"learning_rate": 6.2921994827748e-06,
"loss": 0.2318,
"step": 556
},
{
"epoch": 0.8350824587706147,
"grad_norm": 1.3978880053168186,
"learning_rate": 6.280820856012277e-06,
"loss": 0.2977,
"step": 557
},
{
"epoch": 0.8365817091454273,
"grad_norm": 1.2090118832547283,
"learning_rate": 6.269435125686105e-06,
"loss": 0.261,
"step": 558
},
{
"epoch": 0.8380809595202399,
"grad_norm": 1.3985866398226101,
"learning_rate": 6.258042354942708e-06,
"loss": 0.3036,
"step": 559
},
{
"epoch": 0.8395802098950524,
"grad_norm": 1.1606338171512245,
"learning_rate": 6.2466426069675626e-06,
"loss": 0.2477,
"step": 560
},
{
"epoch": 0.841079460269865,
"grad_norm": 1.2752184464154694,
"learning_rate": 6.235235944984835e-06,
"loss": 0.2569,
"step": 561
},
{
"epoch": 0.8425787106446777,
"grad_norm": 1.3606727254695086,
"learning_rate": 6.223822432257043e-06,
"loss": 0.3106,
"step": 562
},
{
"epoch": 0.8440779610194903,
"grad_norm": 1.6737768428007465,
"learning_rate": 6.212402132084697e-06,
"loss": 0.3228,
"step": 563
},
{
"epoch": 0.8455772113943029,
"grad_norm": 1.4872863959750497,
"learning_rate": 6.200975107805951e-06,
"loss": 0.3318,
"step": 564
},
{
"epoch": 0.8470764617691154,
"grad_norm": 1.4190668277366123,
"learning_rate": 6.189541422796254e-06,
"loss": 0.2838,
"step": 565
},
{
"epoch": 0.848575712143928,
"grad_norm": 1.476533938778296,
"learning_rate": 6.1781011404679905e-06,
"loss": 0.345,
"step": 566
},
{
"epoch": 0.8500749625187406,
"grad_norm": 1.4046281735745454,
"learning_rate": 6.16665432427014e-06,
"loss": 0.2948,
"step": 567
},
{
"epoch": 0.8515742128935532,
"grad_norm": 1.3727655219029598,
"learning_rate": 6.155201037687917e-06,
"loss": 0.3222,
"step": 568
},
{
"epoch": 0.8530734632683659,
"grad_norm": 1.1826488043411998,
"learning_rate": 6.1437413442424236e-06,
"loss": 0.2496,
"step": 569
},
{
"epoch": 0.8545727136431784,
"grad_norm": 1.2764505261433423,
"learning_rate": 6.132275307490291e-06,
"loss": 0.2573,
"step": 570
},
{
"epoch": 0.856071964017991,
"grad_norm": 1.4266014279851462,
"learning_rate": 6.120802991023334e-06,
"loss": 0.2758,
"step": 571
},
{
"epoch": 0.8575712143928036,
"grad_norm": 1.3290173029582117,
"learning_rate": 6.109324458468198e-06,
"loss": 0.2859,
"step": 572
},
{
"epoch": 0.8590704647676162,
"grad_norm": 1.4697115370090508,
"learning_rate": 6.097839773485995e-06,
"loss": 0.2775,
"step": 573
},
{
"epoch": 0.8605697151424287,
"grad_norm": 1.5752850012956432,
"learning_rate": 6.086348999771967e-06,
"loss": 0.3346,
"step": 574
},
{
"epoch": 0.8620689655172413,
"grad_norm": 1.36699571040609,
"learning_rate": 6.074852201055121e-06,
"loss": 0.2588,
"step": 575
},
{
"epoch": 0.863568215892054,
"grad_norm": 1.2426740616867487,
"learning_rate": 6.063349441097881e-06,
"loss": 0.2601,
"step": 576
},
{
"epoch": 0.8650674662668666,
"grad_norm": 1.4919809348981423,
"learning_rate": 6.051840783695731e-06,
"loss": 0.2513,
"step": 577
},
{
"epoch": 0.8665667166416792,
"grad_norm": 1.5345577792571532,
"learning_rate": 6.040326292676865e-06,
"loss": 0.2474,
"step": 578
},
{
"epoch": 0.8680659670164917,
"grad_norm": 1.6813509135438214,
"learning_rate": 6.028806031901829e-06,
"loss": 0.3529,
"step": 579
},
{
"epoch": 0.8695652173913043,
"grad_norm": 1.3796283386011006,
"learning_rate": 6.0172800652631706e-06,
"loss": 0.2799,
"step": 580
},
{
"epoch": 0.8710644677661169,
"grad_norm": 1.5983920234793207,
"learning_rate": 6.005748456685077e-06,
"loss": 0.2482,
"step": 581
},
{
"epoch": 0.8725637181409296,
"grad_norm": 1.49492444093455,
"learning_rate": 5.994211270123034e-06,
"loss": 0.34,
"step": 582
},
{
"epoch": 0.8740629685157422,
"grad_norm": 1.5280370609487266,
"learning_rate": 5.9826685695634575e-06,
"loss": 0.2707,
"step": 583
},
{
"epoch": 0.8755622188905547,
"grad_norm": 1.4115095606097392,
"learning_rate": 5.971120419023349e-06,
"loss": 0.3001,
"step": 584
},
{
"epoch": 0.8770614692653673,
"grad_norm": 1.0267416900777009,
"learning_rate": 5.959566882549936e-06,
"loss": 0.2554,
"step": 585
},
{
"epoch": 0.8785607196401799,
"grad_norm": 1.4461370111927105,
"learning_rate": 5.948008024220311e-06,
"loss": 0.2667,
"step": 586
},
{
"epoch": 0.8800599700149925,
"grad_norm": 1.2537964237042767,
"learning_rate": 5.936443908141088e-06,
"loss": 0.2505,
"step": 587
},
{
"epoch": 0.881559220389805,
"grad_norm": 1.210713323399033,
"learning_rate": 5.924874598448038e-06,
"loss": 0.2892,
"step": 588
},
{
"epoch": 0.8830584707646177,
"grad_norm": 1.2982578846962085,
"learning_rate": 5.913300159305741e-06,
"loss": 0.296,
"step": 589
},
{
"epoch": 0.8845577211394303,
"grad_norm": 1.3920112691596835,
"learning_rate": 5.901720654907217e-06,
"loss": 0.2823,
"step": 590
},
{
"epoch": 0.8860569715142429,
"grad_norm": 1.4144356205847997,
"learning_rate": 5.8901361494735874e-06,
"loss": 0.2838,
"step": 591
},
{
"epoch": 0.8875562218890555,
"grad_norm": 1.8116464085465231,
"learning_rate": 5.878546707253704e-06,
"loss": 0.3302,
"step": 592
},
{
"epoch": 0.889055472263868,
"grad_norm": 1.6207641114352942,
"learning_rate": 5.8669523925238e-06,
"loss": 0.326,
"step": 593
},
{
"epoch": 0.8905547226386806,
"grad_norm": 1.2974508907320734,
"learning_rate": 5.855353269587134e-06,
"loss": 0.2569,
"step": 594
},
{
"epoch": 0.8920539730134932,
"grad_norm": 1.3680649334588744,
"learning_rate": 5.843749402773629e-06,
"loss": 0.2908,
"step": 595
},
{
"epoch": 0.8935532233883059,
"grad_norm": 1.4273879867863084,
"learning_rate": 5.8321408564395165e-06,
"loss": 0.2769,
"step": 596
},
{
"epoch": 0.8950524737631185,
"grad_norm": 1.4582034105361414,
"learning_rate": 5.820527694966988e-06,
"loss": 0.2787,
"step": 597
},
{
"epoch": 0.896551724137931,
"grad_norm": 1.402381583836049,
"learning_rate": 5.808909982763825e-06,
"loss": 0.3137,
"step": 598
},
{
"epoch": 0.8980509745127436,
"grad_norm": 1.3452237620825134,
"learning_rate": 5.797287784263047e-06,
"loss": 0.2981,
"step": 599
},
{
"epoch": 0.8995502248875562,
"grad_norm": 1.520231591052473,
"learning_rate": 5.785661163922558e-06,
"loss": 0.3367,
"step": 600
},
{
"epoch": 0.8995502248875562,
"eval_loss": 0.29206138849258423,
"eval_runtime": 9.5457,
"eval_samples_per_second": 5.657,
"eval_steps_per_second": 1.467,
"step": 600
},
{
"epoch": 0.9010494752623688,
"grad_norm": 1.6572680676451537,
"learning_rate": 5.774030186224786e-06,
"loss": 0.3058,
"step": 601
},
{
"epoch": 0.9025487256371814,
"grad_norm": 1.185723814962086,
"learning_rate": 5.762394915676325e-06,
"loss": 0.2436,
"step": 602
},
{
"epoch": 0.904047976011994,
"grad_norm": 1.39517738031953,
"learning_rate": 5.750755416807575e-06,
"loss": 0.2776,
"step": 603
},
{
"epoch": 0.9055472263868066,
"grad_norm": 1.4495451198548506,
"learning_rate": 5.7391117541723914e-06,
"loss": 0.2422,
"step": 604
},
{
"epoch": 0.9070464767616192,
"grad_norm": 1.6099728259980806,
"learning_rate": 5.727463992347719e-06,
"loss": 0.3282,
"step": 605
},
{
"epoch": 0.9085457271364318,
"grad_norm": 1.2759026133924352,
"learning_rate": 5.715812195933238e-06,
"loss": 0.2487,
"step": 606
},
{
"epoch": 0.9100449775112444,
"grad_norm": 1.5890512567327135,
"learning_rate": 5.704156429551004e-06,
"loss": 0.3463,
"step": 607
},
{
"epoch": 0.9115442278860569,
"grad_norm": 1.2349726824993277,
"learning_rate": 5.692496757845092e-06,
"loss": 0.2183,
"step": 608
},
{
"epoch": 0.9130434782608695,
"grad_norm": 1.5231664312018351,
"learning_rate": 5.680833245481234e-06,
"loss": 0.3024,
"step": 609
},
{
"epoch": 0.9145427286356822,
"grad_norm": 1.7511007657264783,
"learning_rate": 5.6691659571464655e-06,
"loss": 0.3781,
"step": 610
},
{
"epoch": 0.9160419790104948,
"grad_norm": 1.262964038541314,
"learning_rate": 5.657494957548761e-06,
"loss": 0.2968,
"step": 611
},
{
"epoch": 0.9175412293853074,
"grad_norm": 1.5010815792926107,
"learning_rate": 5.645820311416681e-06,
"loss": 0.2283,
"step": 612
},
{
"epoch": 0.9190404797601199,
"grad_norm": 1.4230405823122065,
"learning_rate": 5.63414208349901e-06,
"loss": 0.3058,
"step": 613
},
{
"epoch": 0.9205397301349325,
"grad_norm": 1.5061316729401288,
"learning_rate": 5.622460338564393e-06,
"loss": 0.2733,
"step": 614
},
{
"epoch": 0.9220389805097451,
"grad_norm": 1.3792177007935027,
"learning_rate": 5.610775141400986e-06,
"loss": 0.2475,
"step": 615
},
{
"epoch": 0.9235382308845578,
"grad_norm": 1.3503323435812955,
"learning_rate": 5.599086556816089e-06,
"loss": 0.2866,
"step": 616
},
{
"epoch": 0.9250374812593704,
"grad_norm": 1.2673189794772455,
"learning_rate": 5.587394649635789e-06,
"loss": 0.2957,
"step": 617
},
{
"epoch": 0.9265367316341829,
"grad_norm": 1.4641577524105518,
"learning_rate": 5.575699484704599e-06,
"loss": 0.2157,
"step": 618
},
{
"epoch": 0.9280359820089955,
"grad_norm": 1.3670619366737466,
"learning_rate": 5.564001126885106e-06,
"loss": 0.2519,
"step": 619
},
{
"epoch": 0.9295352323838081,
"grad_norm": 1.3066189579332126,
"learning_rate": 5.552299641057596e-06,
"loss": 0.3019,
"step": 620
},
{
"epoch": 0.9310344827586207,
"grad_norm": 1.6654792134736487,
"learning_rate": 5.540595092119709e-06,
"loss": 0.2605,
"step": 621
},
{
"epoch": 0.9325337331334332,
"grad_norm": 1.6688624360319917,
"learning_rate": 5.5288875449860745e-06,
"loss": 0.2787,
"step": 622
},
{
"epoch": 0.9340329835082459,
"grad_norm": 1.3510953241995245,
"learning_rate": 5.517177064587945e-06,
"loss": 0.2423,
"step": 623
},
{
"epoch": 0.9355322338830585,
"grad_norm": 1.124714667302018,
"learning_rate": 5.505463715872846e-06,
"loss": 0.235,
"step": 624
},
{
"epoch": 0.9370314842578711,
"grad_norm": 1.4801862748049064,
"learning_rate": 5.493747563804211e-06,
"loss": 0.281,
"step": 625
},
{
"epoch": 0.9385307346326837,
"grad_norm": 1.1040049089982813,
"learning_rate": 5.482028673361015e-06,
"loss": 0.2641,
"step": 626
},
{
"epoch": 0.9400299850074962,
"grad_norm": 1.340016529324993,
"learning_rate": 5.470307109537427e-06,
"loss": 0.2946,
"step": 627
},
{
"epoch": 0.9415292353823088,
"grad_norm": 1.430555729700914,
"learning_rate": 5.45858293734244e-06,
"loss": 0.2422,
"step": 628
},
{
"epoch": 0.9430284857571214,
"grad_norm": 1.5769826874632167,
"learning_rate": 5.446856221799515e-06,
"loss": 0.3112,
"step": 629
},
{
"epoch": 0.9445277361319341,
"grad_norm": 1.4620846536099739,
"learning_rate": 5.435127027946215e-06,
"loss": 0.2896,
"step": 630
},
{
"epoch": 0.9460269865067467,
"grad_norm": 1.3737452607442782,
"learning_rate": 5.423395420833853e-06,
"loss": 0.2799,
"step": 631
},
{
"epoch": 0.9475262368815592,
"grad_norm": 1.7102252286344872,
"learning_rate": 5.411661465527123e-06,
"loss": 0.3204,
"step": 632
},
{
"epoch": 0.9490254872563718,
"grad_norm": 1.4271957765913807,
"learning_rate": 5.39992522710374e-06,
"loss": 0.2968,
"step": 633
},
{
"epoch": 0.9505247376311844,
"grad_norm": 1.6668553497999354,
"learning_rate": 5.38818677065409e-06,
"loss": 0.326,
"step": 634
},
{
"epoch": 0.952023988005997,
"grad_norm": 1.3656853429793527,
"learning_rate": 5.376446161280851e-06,
"loss": 0.2679,
"step": 635
},
{
"epoch": 0.9535232383808095,
"grad_norm": 1.3480865579714252,
"learning_rate": 5.364703464098645e-06,
"loss": 0.306,
"step": 636
},
{
"epoch": 0.9550224887556222,
"grad_norm": 1.4812025245339286,
"learning_rate": 5.352958744233673e-06,
"loss": 0.2744,
"step": 637
},
{
"epoch": 0.9565217391304348,
"grad_norm": 1.2805349985156824,
"learning_rate": 5.341212066823356e-06,
"loss": 0.3079,
"step": 638
},
{
"epoch": 0.9580209895052474,
"grad_norm": 1.4695819034171325,
"learning_rate": 5.329463497015969e-06,
"loss": 0.2546,
"step": 639
},
{
"epoch": 0.95952023988006,
"grad_norm": 1.6943571642681556,
"learning_rate": 5.317713099970283e-06,
"loss": 0.2819,
"step": 640
},
{
"epoch": 0.9610194902548725,
"grad_norm": 1.0308594634641264,
"learning_rate": 5.305960940855205e-06,
"loss": 0.2323,
"step": 641
},
{
"epoch": 0.9625187406296851,
"grad_norm": 1.5361826846459423,
"learning_rate": 5.294207084849412e-06,
"loss": 0.2909,
"step": 642
},
{
"epoch": 0.9640179910044977,
"grad_norm": 1.4262667808104355,
"learning_rate": 5.282451597140994e-06,
"loss": 0.28,
"step": 643
},
{
"epoch": 0.9655172413793104,
"grad_norm": 1.726419979057364,
"learning_rate": 5.270694542927089e-06,
"loss": 0.3445,
"step": 644
},
{
"epoch": 0.967016491754123,
"grad_norm": 1.6777590573778045,
"learning_rate": 5.258935987413524e-06,
"loss": 0.312,
"step": 645
},
{
"epoch": 0.9685157421289355,
"grad_norm": 1.2723822863902055,
"learning_rate": 5.247175995814452e-06,
"loss": 0.2866,
"step": 646
},
{
"epoch": 0.9700149925037481,
"grad_norm": 1.4904091995112534,
"learning_rate": 5.235414633351992e-06,
"loss": 0.2914,
"step": 647
},
{
"epoch": 0.9715142428785607,
"grad_norm": 1.292447279724776,
"learning_rate": 5.223651965255864e-06,
"loss": 0.2833,
"step": 648
},
{
"epoch": 0.9730134932533733,
"grad_norm": 1.3044142845118825,
"learning_rate": 5.211888056763029e-06,
"loss": 0.219,
"step": 649
},
{
"epoch": 0.974512743628186,
"grad_norm": 1.442499937194901,
"learning_rate": 5.20012297311733e-06,
"loss": 0.267,
"step": 650
},
{
"epoch": 0.9760119940029985,
"grad_norm": 1.068811635820371,
"learning_rate": 5.188356779569125e-06,
"loss": 0.2681,
"step": 651
},
{
"epoch": 0.9775112443778111,
"grad_norm": 1.4833078434438498,
"learning_rate": 5.176589541374929e-06,
"loss": 0.3169,
"step": 652
},
{
"epoch": 0.9790104947526237,
"grad_norm": 1.588644516704138,
"learning_rate": 5.164821323797051e-06,
"loss": 0.3368,
"step": 653
},
{
"epoch": 0.9805097451274363,
"grad_norm": 1.4226545240627448,
"learning_rate": 5.1530521921032305e-06,
"loss": 0.27,
"step": 654
},
{
"epoch": 0.9820089955022488,
"grad_norm": 1.3572773713708628,
"learning_rate": 5.141282211566276e-06,
"loss": 0.2758,
"step": 655
},
{
"epoch": 0.9835082458770614,
"grad_norm": 1.789911225991221,
"learning_rate": 5.129511447463705e-06,
"loss": 0.2953,
"step": 656
},
{
"epoch": 0.9850074962518741,
"grad_norm": 1.5937283093067185,
"learning_rate": 5.117739965077382e-06,
"loss": 0.2746,
"step": 657
},
{
"epoch": 0.9865067466266867,
"grad_norm": 1.5824857897997608,
"learning_rate": 5.105967829693155e-06,
"loss": 0.3011,
"step": 658
},
{
"epoch": 0.9880059970014993,
"grad_norm": 1.564631220436148,
"learning_rate": 5.0941951066004906e-06,
"loss": 0.3024,
"step": 659
},
{
"epoch": 0.9895052473763118,
"grad_norm": 1.4723213190521782,
"learning_rate": 5.082421861092116e-06,
"loss": 0.3513,
"step": 660
},
{
"epoch": 0.9910044977511244,
"grad_norm": 1.3246585112656946,
"learning_rate": 5.0706481584636605e-06,
"loss": 0.2978,
"step": 661
},
{
"epoch": 0.992503748125937,
"grad_norm": 1.294485905427711,
"learning_rate": 5.0588740640132805e-06,
"loss": 0.3248,
"step": 662
},
{
"epoch": 0.9940029985007496,
"grad_norm": 1.371441396786382,
"learning_rate": 5.047099643041312e-06,
"loss": 0.2343,
"step": 663
},
{
"epoch": 0.9955022488755623,
"grad_norm": 1.232279769034759,
"learning_rate": 5.0353249608499e-06,
"loss": 0.2847,
"step": 664
},
{
"epoch": 0.9970014992503748,
"grad_norm": 1.5408042440355365,
"learning_rate": 5.023550082742637e-06,
"loss": 0.4079,
"step": 665
},
{
"epoch": 0.9985007496251874,
"grad_norm": 1.5975441677311908,
"learning_rate": 5.011775074024202e-06,
"loss": 0.3385,
"step": 666
},
{
"epoch": 1.0,
"grad_norm": 1.1717472846174595,
"learning_rate": 5e-06,
"loss": 0.1856,
"step": 667
},
{
"epoch": 1.0014992503748126,
"grad_norm": 1.2245141748896478,
"learning_rate": 4.988224925975799e-06,
"loss": 0.1454,
"step": 668
},
{
"epoch": 1.0029985007496252,
"grad_norm": 1.113035633567804,
"learning_rate": 4.976449917257365e-06,
"loss": 0.1256,
"step": 669
},
{
"epoch": 1.0044977511244377,
"grad_norm": 0.9840302945774542,
"learning_rate": 4.964675039150102e-06,
"loss": 0.1383,
"step": 670
},
{
"epoch": 1.0059970014992503,
"grad_norm": 1.0108761114865439,
"learning_rate": 4.952900356958689e-06,
"loss": 0.1429,
"step": 671
},
{
"epoch": 1.0074962518740629,
"grad_norm": 1.3303373350497616,
"learning_rate": 4.941125935986721e-06,
"loss": 0.1636,
"step": 672
},
{
"epoch": 1.0089955022488755,
"grad_norm": 1.0618850415016292,
"learning_rate": 4.929351841536342e-06,
"loss": 0.122,
"step": 673
},
{
"epoch": 1.0104947526236883,
"grad_norm": 1.0597281702360088,
"learning_rate": 4.917578138907884e-06,
"loss": 0.1423,
"step": 674
},
{
"epoch": 1.0119940029985008,
"grad_norm": 1.4352697889938788,
"learning_rate": 4.90580489339951e-06,
"loss": 0.1556,
"step": 675
},
{
"epoch": 1.0134932533733134,
"grad_norm": 1.555494683142059,
"learning_rate": 4.894032170306846e-06,
"loss": 0.134,
"step": 676
},
{
"epoch": 1.014992503748126,
"grad_norm": 1.370821379224341,
"learning_rate": 4.882260034922618e-06,
"loss": 0.133,
"step": 677
},
{
"epoch": 1.0164917541229386,
"grad_norm": 1.4335702429296835,
"learning_rate": 4.870488552536296e-06,
"loss": 0.1298,
"step": 678
},
{
"epoch": 1.0179910044977512,
"grad_norm": 1.52947611793239,
"learning_rate": 4.858717788433725e-06,
"loss": 0.1861,
"step": 679
},
{
"epoch": 1.0194902548725637,
"grad_norm": 1.4092638210180686,
"learning_rate": 4.846947807896771e-06,
"loss": 0.1511,
"step": 680
},
{
"epoch": 1.0209895052473763,
"grad_norm": 1.7306575478915662,
"learning_rate": 4.83517867620295e-06,
"loss": 0.1444,
"step": 681
},
{
"epoch": 1.0224887556221889,
"grad_norm": 1.1733329564563357,
"learning_rate": 4.823410458625072e-06,
"loss": 0.1043,
"step": 682
},
{
"epoch": 1.0239880059970015,
"grad_norm": 1.322557279313773,
"learning_rate": 4.811643220430877e-06,
"loss": 0.1202,
"step": 683
},
{
"epoch": 1.025487256371814,
"grad_norm": 1.62584402069839,
"learning_rate": 4.7998770268826726e-06,
"loss": 0.1852,
"step": 684
},
{
"epoch": 1.0269865067466266,
"grad_norm": 1.417400006454122,
"learning_rate": 4.788111943236973e-06,
"loss": 0.1225,
"step": 685
},
{
"epoch": 1.0284857571214392,
"grad_norm": 1.2217123888670718,
"learning_rate": 4.7763480347441395e-06,
"loss": 0.1416,
"step": 686
},
{
"epoch": 1.0299850074962518,
"grad_norm": 1.2785152245174605,
"learning_rate": 4.7645853666480104e-06,
"loss": 0.1338,
"step": 687
},
{
"epoch": 1.0314842578710646,
"grad_norm": 1.3155022956274116,
"learning_rate": 4.752824004185548e-06,
"loss": 0.1599,
"step": 688
},
{
"epoch": 1.0329835082458771,
"grad_norm": 1.0631267096170913,
"learning_rate": 4.7410640125864785e-06,
"loss": 0.0865,
"step": 689
},
{
"epoch": 1.0344827586206897,
"grad_norm": 1.3534102460997244,
"learning_rate": 4.729305457072913e-06,
"loss": 0.1871,
"step": 690
},
{
"epoch": 1.0359820089955023,
"grad_norm": 1.1008608232400132,
"learning_rate": 4.717548402859008e-06,
"loss": 0.1382,
"step": 691
},
{
"epoch": 1.0374812593703149,
"grad_norm": 1.0930736447370444,
"learning_rate": 4.7057929151505895e-06,
"loss": 0.1673,
"step": 692
},
{
"epoch": 1.0389805097451275,
"grad_norm": 1.2562782943155963,
"learning_rate": 4.694039059144797e-06,
"loss": 0.1536,
"step": 693
},
{
"epoch": 1.04047976011994,
"grad_norm": 1.17150972869752,
"learning_rate": 4.6822869000297185e-06,
"loss": 0.1241,
"step": 694
},
{
"epoch": 1.0419790104947526,
"grad_norm": 1.3078257332527907,
"learning_rate": 4.670536502984033e-06,
"loss": 0.127,
"step": 695
},
{
"epoch": 1.0434782608695652,
"grad_norm": 1.20399047700232,
"learning_rate": 4.6587879331766465e-06,
"loss": 0.1649,
"step": 696
},
{
"epoch": 1.0449775112443778,
"grad_norm": 1.2798756895600847,
"learning_rate": 4.647041255766329e-06,
"loss": 0.1569,
"step": 697
},
{
"epoch": 1.0464767616191903,
"grad_norm": 1.2836422968151344,
"learning_rate": 4.6352965359013576e-06,
"loss": 0.1531,
"step": 698
},
{
"epoch": 1.047976011994003,
"grad_norm": 1.2656982740498037,
"learning_rate": 4.623553838719151e-06,
"loss": 0.1382,
"step": 699
},
{
"epoch": 1.0494752623688155,
"grad_norm": 1.1710073058457482,
"learning_rate": 4.611813229345911e-06,
"loss": 0.1284,
"step": 700
},
{
"epoch": 1.050974512743628,
"grad_norm": 1.2173427215843842,
"learning_rate": 4.6000747728962606e-06,
"loss": 0.1451,
"step": 701
},
{
"epoch": 1.0524737631184409,
"grad_norm": 1.3085766303922433,
"learning_rate": 4.588338534472878e-06,
"loss": 0.1634,
"step": 702
},
{
"epoch": 1.0539730134932535,
"grad_norm": 1.294598563303439,
"learning_rate": 4.576604579166147e-06,
"loss": 0.1555,
"step": 703
},
{
"epoch": 1.055472263868066,
"grad_norm": 1.3608846742813256,
"learning_rate": 4.564872972053786e-06,
"loss": 0.137,
"step": 704
},
{
"epoch": 1.0569715142428786,
"grad_norm": 1.3254766227344228,
"learning_rate": 4.553143778200486e-06,
"loss": 0.1928,
"step": 705
},
{
"epoch": 1.0584707646176912,
"grad_norm": 1.4520394103397216,
"learning_rate": 4.541417062657561e-06,
"loss": 0.1295,
"step": 706
},
{
"epoch": 1.0599700149925038,
"grad_norm": 1.4398136951048757,
"learning_rate": 4.529692890462574e-06,
"loss": 0.1554,
"step": 707
},
{
"epoch": 1.0614692653673163,
"grad_norm": 1.1500875677970415,
"learning_rate": 4.5179713266389866e-06,
"loss": 0.1238,
"step": 708
},
{
"epoch": 1.062968515742129,
"grad_norm": 1.264839059509746,
"learning_rate": 4.50625243619579e-06,
"loss": 0.0976,
"step": 709
},
{
"epoch": 1.0644677661169415,
"grad_norm": 1.411189676587246,
"learning_rate": 4.494536284127155e-06,
"loss": 0.157,
"step": 710
},
{
"epoch": 1.065967016491754,
"grad_norm": 1.3419565690016924,
"learning_rate": 4.4828229354120565e-06,
"loss": 0.116,
"step": 711
},
{
"epoch": 1.0674662668665666,
"grad_norm": 1.4683125069720693,
"learning_rate": 4.471112455013928e-06,
"loss": 0.1419,
"step": 712
},
{
"epoch": 1.0689655172413792,
"grad_norm": 1.2795421939766032,
"learning_rate": 4.459404907880293e-06,
"loss": 0.1251,
"step": 713
},
{
"epoch": 1.0704647676161918,
"grad_norm": 1.4847504711631283,
"learning_rate": 4.447700358942407e-06,
"loss": 0.206,
"step": 714
},
{
"epoch": 1.0719640179910046,
"grad_norm": 1.4538062911622482,
"learning_rate": 4.435998873114895e-06,
"loss": 0.1442,
"step": 715
},
{
"epoch": 1.0734632683658172,
"grad_norm": 1.4008873503791266,
"learning_rate": 4.424300515295401e-06,
"loss": 0.1526,
"step": 716
},
{
"epoch": 1.0749625187406298,
"grad_norm": 1.347711770180375,
"learning_rate": 4.412605350364213e-06,
"loss": 0.1427,
"step": 717
},
{
"epoch": 1.0764617691154423,
"grad_norm": 1.3360204372994373,
"learning_rate": 4.400913443183913e-06,
"loss": 0.1669,
"step": 718
},
{
"epoch": 1.077961019490255,
"grad_norm": 1.414970873310588,
"learning_rate": 4.389224858599015e-06,
"loss": 0.1423,
"step": 719
},
{
"epoch": 1.0794602698650675,
"grad_norm": 1.1304666933798686,
"learning_rate": 4.377539661435608e-06,
"loss": 0.1039,
"step": 720
},
{
"epoch": 1.08095952023988,
"grad_norm": 1.290125072577748,
"learning_rate": 4.365857916500991e-06,
"loss": 0.1141,
"step": 721
},
{
"epoch": 1.0824587706146926,
"grad_norm": 1.3637566768919038,
"learning_rate": 4.35417968858332e-06,
"loss": 0.1979,
"step": 722
},
{
"epoch": 1.0839580209895052,
"grad_norm": 1.1222997413654716,
"learning_rate": 4.3425050424512405e-06,
"loss": 0.1318,
"step": 723
},
{
"epoch": 1.0854572713643178,
"grad_norm": 1.3007268919799113,
"learning_rate": 4.330834042853537e-06,
"loss": 0.1541,
"step": 724
},
{
"epoch": 1.0869565217391304,
"grad_norm": 1.5410675815308512,
"learning_rate": 4.319166754518768e-06,
"loss": 0.1427,
"step": 725
},
{
"epoch": 1.088455772113943,
"grad_norm": 1.3800795797956538,
"learning_rate": 4.30750324215491e-06,
"loss": 0.1304,
"step": 726
},
{
"epoch": 1.0899550224887555,
"grad_norm": 1.7373486522086135,
"learning_rate": 4.295843570448998e-06,
"loss": 0.1774,
"step": 727
},
{
"epoch": 1.0914542728635683,
"grad_norm": 1.2144628359769445,
"learning_rate": 4.284187804066764e-06,
"loss": 0.1455,
"step": 728
},
{
"epoch": 1.092953523238381,
"grad_norm": 1.3030437140567384,
"learning_rate": 4.272536007652281e-06,
"loss": 0.1348,
"step": 729
},
{
"epoch": 1.0944527736131935,
"grad_norm": 1.2388238391414266,
"learning_rate": 4.260888245827608e-06,
"loss": 0.1254,
"step": 730
},
{
"epoch": 1.095952023988006,
"grad_norm": 1.3662430679102924,
"learning_rate": 4.249244583192425e-06,
"loss": 0.1819,
"step": 731
},
{
"epoch": 1.0974512743628186,
"grad_norm": 1.222181566924626,
"learning_rate": 4.237605084323676e-06,
"loss": 0.1413,
"step": 732
},
{
"epoch": 1.0989505247376312,
"grad_norm": 1.5381720302103399,
"learning_rate": 4.225969813775215e-06,
"loss": 0.1324,
"step": 733
},
{
"epoch": 1.1004497751124438,
"grad_norm": 1.2618776650323837,
"learning_rate": 4.214338836077444e-06,
"loss": 0.137,
"step": 734
},
{
"epoch": 1.1019490254872564,
"grad_norm": 1.4199292581983365,
"learning_rate": 4.202712215736955e-06,
"loss": 0.1899,
"step": 735
},
{
"epoch": 1.103448275862069,
"grad_norm": 1.4016758647648953,
"learning_rate": 4.191090017236177e-06,
"loss": 0.1501,
"step": 736
},
{
"epoch": 1.1049475262368815,
"grad_norm": 1.2803781801023755,
"learning_rate": 4.1794723050330125e-06,
"loss": 0.1513,
"step": 737
},
{
"epoch": 1.106446776611694,
"grad_norm": 1.2124474695852974,
"learning_rate": 4.167859143560484e-06,
"loss": 0.1434,
"step": 738
},
{
"epoch": 1.1079460269865067,
"grad_norm": 1.1693180350237993,
"learning_rate": 4.1562505972263735e-06,
"loss": 0.105,
"step": 739
},
{
"epoch": 1.1094452773613193,
"grad_norm": 1.266898243587645,
"learning_rate": 4.144646730412868e-06,
"loss": 0.1443,
"step": 740
},
{
"epoch": 1.1109445277361318,
"grad_norm": 1.296462545853387,
"learning_rate": 4.133047607476202e-06,
"loss": 0.1606,
"step": 741
},
{
"epoch": 1.1124437781109444,
"grad_norm": 1.1266501020062736,
"learning_rate": 4.121453292746297e-06,
"loss": 0.1617,
"step": 742
},
{
"epoch": 1.1139430284857572,
"grad_norm": 1.1614340793928641,
"learning_rate": 4.109863850526413e-06,
"loss": 0.1605,
"step": 743
},
{
"epoch": 1.1154422788605698,
"grad_norm": 1.4436812287795313,
"learning_rate": 4.098279345092783e-06,
"loss": 0.1492,
"step": 744
},
{
"epoch": 1.1169415292353824,
"grad_norm": 1.3218417009167271,
"learning_rate": 4.086699840694262e-06,
"loss": 0.1143,
"step": 745
},
{
"epoch": 1.118440779610195,
"grad_norm": 1.3269621462232215,
"learning_rate": 4.075125401551963e-06,
"loss": 0.1546,
"step": 746
},
{
"epoch": 1.1199400299850075,
"grad_norm": 1.2313134265269736,
"learning_rate": 4.063556091858914e-06,
"loss": 0.1164,
"step": 747
},
{
"epoch": 1.12143928035982,
"grad_norm": 1.3666671026310135,
"learning_rate": 4.051991975779691e-06,
"loss": 0.1404,
"step": 748
},
{
"epoch": 1.1229385307346327,
"grad_norm": 1.5009915078741978,
"learning_rate": 4.040433117450066e-06,
"loss": 0.1644,
"step": 749
},
{
"epoch": 1.1244377811094453,
"grad_norm": 1.4273688853548707,
"learning_rate": 4.0288795809766516e-06,
"loss": 0.1543,
"step": 750
},
{
"epoch": 1.1259370314842578,
"grad_norm": 1.2141199766632593,
"learning_rate": 4.017331430436543e-06,
"loss": 0.124,
"step": 751
},
{
"epoch": 1.1274362818590704,
"grad_norm": 1.4237578114436968,
"learning_rate": 4.005788729876968e-06,
"loss": 0.1836,
"step": 752
},
{
"epoch": 1.128935532233883,
"grad_norm": 1.2206638311513194,
"learning_rate": 3.994251543314925e-06,
"loss": 0.13,
"step": 753
},
{
"epoch": 1.1304347826086956,
"grad_norm": 1.4173756422782844,
"learning_rate": 3.982719934736832e-06,
"loss": 0.1342,
"step": 754
},
{
"epoch": 1.1319340329835081,
"grad_norm": 1.4287245590548212,
"learning_rate": 3.971193968098172e-06,
"loss": 0.1729,
"step": 755
},
{
"epoch": 1.133433283358321,
"grad_norm": 1.2489573382268553,
"learning_rate": 3.959673707323135e-06,
"loss": 0.2043,
"step": 756
},
{
"epoch": 1.1349325337331335,
"grad_norm": 1.232882776585709,
"learning_rate": 3.948159216304269e-06,
"loss": 0.1449,
"step": 757
},
{
"epoch": 1.136431784107946,
"grad_norm": 1.5046861484890637,
"learning_rate": 3.93665055890212e-06,
"loss": 0.1359,
"step": 758
},
{
"epoch": 1.1379310344827587,
"grad_norm": 1.4726306281157244,
"learning_rate": 3.92514779894488e-06,
"loss": 0.134,
"step": 759
},
{
"epoch": 1.1394302848575713,
"grad_norm": 1.2979951757761485,
"learning_rate": 3.9136510002280344e-06,
"loss": 0.1884,
"step": 760
},
{
"epoch": 1.1409295352323838,
"grad_norm": 1.2982290747764529,
"learning_rate": 3.902160226514007e-06,
"loss": 0.1605,
"step": 761
},
{
"epoch": 1.1424287856071964,
"grad_norm": 1.2325236048172896,
"learning_rate": 3.8906755415318045e-06,
"loss": 0.1595,
"step": 762
},
{
"epoch": 1.143928035982009,
"grad_norm": 1.1882494094745506,
"learning_rate": 3.8791970089766665e-06,
"loss": 0.129,
"step": 763
},
{
"epoch": 1.1454272863568216,
"grad_norm": 1.7268601633886274,
"learning_rate": 3.86772469250971e-06,
"loss": 0.1698,
"step": 764
},
{
"epoch": 1.1469265367316341,
"grad_norm": 1.2228776128354193,
"learning_rate": 3.856258655757578e-06,
"loss": 0.1007,
"step": 765
},
{
"epoch": 1.1484257871064467,
"grad_norm": 1.383635860339973,
"learning_rate": 3.844798962312085e-06,
"loss": 0.1665,
"step": 766
},
{
"epoch": 1.1499250374812593,
"grad_norm": 1.2720059341262018,
"learning_rate": 3.833345675729863e-06,
"loss": 0.1345,
"step": 767
},
{
"epoch": 1.1514242878560719,
"grad_norm": 1.3231306715546778,
"learning_rate": 3.821898859532013e-06,
"loss": 0.129,
"step": 768
},
{
"epoch": 1.1529235382308847,
"grad_norm": 1.2768309771137538,
"learning_rate": 3.8104585772037493e-06,
"loss": 0.1433,
"step": 769
},
{
"epoch": 1.1544227886056972,
"grad_norm": 1.2978614906648258,
"learning_rate": 3.7990248921940485e-06,
"loss": 0.1528,
"step": 770
},
{
"epoch": 1.1559220389805098,
"grad_norm": 1.1227863019684725,
"learning_rate": 3.787597867915303e-06,
"loss": 0.1352,
"step": 771
},
{
"epoch": 1.1574212893553224,
"grad_norm": 1.4774070389173044,
"learning_rate": 3.7761775677429567e-06,
"loss": 0.1518,
"step": 772
},
{
"epoch": 1.158920539730135,
"grad_norm": 1.3285900564381639,
"learning_rate": 3.7647640550151666e-06,
"loss": 0.1182,
"step": 773
},
{
"epoch": 1.1604197901049476,
"grad_norm": 1.2741394206696637,
"learning_rate": 3.7533573930324395e-06,
"loss": 0.1264,
"step": 774
},
{
"epoch": 1.1619190404797601,
"grad_norm": 1.4724544443053296,
"learning_rate": 3.7419576450572924e-06,
"loss": 0.1437,
"step": 775
},
{
"epoch": 1.1634182908545727,
"grad_norm": 1.2373312789607587,
"learning_rate": 3.7305648743138966e-06,
"loss": 0.1411,
"step": 776
},
{
"epoch": 1.1649175412293853,
"grad_norm": 1.5983303644310531,
"learning_rate": 3.7191791439877236e-06,
"loss": 0.1421,
"step": 777
},
{
"epoch": 1.1664167916041979,
"grad_norm": 1.2040821528942203,
"learning_rate": 3.7078005172252015e-06,
"loss": 0.1414,
"step": 778
},
{
"epoch": 1.1679160419790104,
"grad_norm": 1.3565920153384308,
"learning_rate": 3.6964290571333583e-06,
"loss": 0.1289,
"step": 779
},
{
"epoch": 1.169415292353823,
"grad_norm": 1.494886770034295,
"learning_rate": 3.6850648267794776e-06,
"loss": 0.1493,
"step": 780
},
{
"epoch": 1.1709145427286356,
"grad_norm": 1.2441195402039313,
"learning_rate": 3.673707889190744e-06,
"loss": 0.0992,
"step": 781
},
{
"epoch": 1.1724137931034484,
"grad_norm": 1.3372883034998901,
"learning_rate": 3.662358307353897e-06,
"loss": 0.1191,
"step": 782
},
{
"epoch": 1.1739130434782608,
"grad_norm": 1.2854871350976347,
"learning_rate": 3.6510161442148783e-06,
"loss": 0.1218,
"step": 783
},
{
"epoch": 1.1754122938530736,
"grad_norm": 1.1481541679425193,
"learning_rate": 3.63968146267849e-06,
"loss": 0.1353,
"step": 784
},
{
"epoch": 1.1769115442278861,
"grad_norm": 1.0092289583242011,
"learning_rate": 3.6283543256080334e-06,
"loss": 0.1216,
"step": 785
},
{
"epoch": 1.1784107946026987,
"grad_norm": 1.3898812609035025,
"learning_rate": 3.6170347958249728e-06,
"loss": 0.1583,
"step": 786
},
{
"epoch": 1.1799100449775113,
"grad_norm": 1.2415231843122483,
"learning_rate": 3.605722936108579e-06,
"loss": 0.1418,
"step": 787
},
{
"epoch": 1.1814092953523239,
"grad_norm": 1.465232037061966,
"learning_rate": 3.5944188091955843e-06,
"loss": 0.126,
"step": 788
},
{
"epoch": 1.1829085457271364,
"grad_norm": 1.1131169462327808,
"learning_rate": 3.5831224777798346e-06,
"loss": 0.119,
"step": 789
},
{
"epoch": 1.184407796101949,
"grad_norm": 1.1297393572577206,
"learning_rate": 3.5718340045119416e-06,
"loss": 0.1367,
"step": 790
},
{
"epoch": 1.1859070464767616,
"grad_norm": 1.46635806934035,
"learning_rate": 3.5605534519989327e-06,
"loss": 0.1325,
"step": 791
},
{
"epoch": 1.1874062968515742,
"grad_norm": 1.2573786583650581,
"learning_rate": 3.5492808828039083e-06,
"loss": 0.0993,
"step": 792
},
{
"epoch": 1.1889055472263867,
"grad_norm": 1.3176981497023343,
"learning_rate": 3.538016359445692e-06,
"loss": 0.1317,
"step": 793
},
{
"epoch": 1.1904047976011993,
"grad_norm": 1.1650275353453803,
"learning_rate": 3.5267599443984848e-06,
"loss": 0.1732,
"step": 794
},
{
"epoch": 1.191904047976012,
"grad_norm": 1.3923141810081512,
"learning_rate": 3.5155117000915153e-06,
"loss": 0.171,
"step": 795
},
{
"epoch": 1.1934032983508245,
"grad_norm": 1.1182429512523535,
"learning_rate": 3.5042716889086998e-06,
"loss": 0.1321,
"step": 796
},
{
"epoch": 1.1949025487256373,
"grad_norm": 1.234419843095829,
"learning_rate": 3.493039973188289e-06,
"loss": 0.1052,
"step": 797
},
{
"epoch": 1.1964017991004499,
"grad_norm": 1.406658707936665,
"learning_rate": 3.481816615222533e-06,
"loss": 0.1876,
"step": 798
},
{
"epoch": 1.1979010494752624,
"grad_norm": 1.0328991457308447,
"learning_rate": 3.470601677257323e-06,
"loss": 0.1248,
"step": 799
},
{
"epoch": 1.199400299850075,
"grad_norm": 1.292313377436957,
"learning_rate": 3.459395221491853e-06,
"loss": 0.1591,
"step": 800
},
{
"epoch": 1.199400299850075,
"eval_loss": 0.30602961778640747,
"eval_runtime": 9.5435,
"eval_samples_per_second": 5.658,
"eval_steps_per_second": 1.467,
"step": 800
},
{
"epoch": 1.2008995502248876,
"grad_norm": 1.3058171475272295,
"learning_rate": 3.4481973100782756e-06,
"loss": 0.1576,
"step": 801
},
{
"epoch": 1.2023988005997002,
"grad_norm": 1.3583892270836624,
"learning_rate": 3.4370080051213527e-06,
"loss": 0.2162,
"step": 802
},
{
"epoch": 1.2038980509745127,
"grad_norm": 1.3674456101935875,
"learning_rate": 3.4258273686781156e-06,
"loss": 0.1272,
"step": 803
},
{
"epoch": 1.2053973013493253,
"grad_norm": 1.275046828519697,
"learning_rate": 3.4146554627575207e-06,
"loss": 0.1525,
"step": 804
},
{
"epoch": 1.206896551724138,
"grad_norm": 1.4733582867903916,
"learning_rate": 3.403492349320101e-06,
"loss": 0.1617,
"step": 805
},
{
"epoch": 1.2083958020989505,
"grad_norm": 1.226397831684623,
"learning_rate": 3.392338090277628e-06,
"loss": 0.1026,
"step": 806
},
{
"epoch": 1.209895052473763,
"grad_norm": 1.6112338048507868,
"learning_rate": 3.3811927474927644e-06,
"loss": 0.1653,
"step": 807
},
{
"epoch": 1.2113943028485756,
"grad_norm": 1.3671476703363021,
"learning_rate": 3.3700563827787224e-06,
"loss": 0.1369,
"step": 808
},
{
"epoch": 1.2128935532233882,
"grad_norm": 1.0643585793575752,
"learning_rate": 3.358929057898922e-06,
"loss": 0.1251,
"step": 809
},
{
"epoch": 1.214392803598201,
"grad_norm": 1.1339958530244039,
"learning_rate": 3.3478108345666456e-06,
"loss": 0.1431,
"step": 810
},
{
"epoch": 1.2158920539730136,
"grad_norm": 1.0883168747590415,
"learning_rate": 3.3367017744446995e-06,
"loss": 0.1069,
"step": 811
},
{
"epoch": 1.2173913043478262,
"grad_norm": 1.26438068795269,
"learning_rate": 3.3256019391450696e-06,
"loss": 0.178,
"step": 812
},
{
"epoch": 1.2188905547226387,
"grad_norm": 1.0664372577970027,
"learning_rate": 3.314511390228578e-06,
"loss": 0.1011,
"step": 813
},
{
"epoch": 1.2203898050974513,
"grad_norm": 1.3331137347043034,
"learning_rate": 3.303430189204545e-06,
"loss": 0.117,
"step": 814
},
{
"epoch": 1.221889055472264,
"grad_norm": 1.3304820446438348,
"learning_rate": 3.2923583975304474e-06,
"loss": 0.171,
"step": 815
},
{
"epoch": 1.2233883058470765,
"grad_norm": 1.1062517912626064,
"learning_rate": 3.2812960766115747e-06,
"loss": 0.1195,
"step": 816
},
{
"epoch": 1.224887556221889,
"grad_norm": 1.8558570146937945,
"learning_rate": 3.270243287800693e-06,
"loss": 0.18,
"step": 817
},
{
"epoch": 1.2263868065967016,
"grad_norm": 1.2786157676011234,
"learning_rate": 3.2592000923976997e-06,
"loss": 0.1618,
"step": 818
},
{
"epoch": 1.2278860569715142,
"grad_norm": 1.4796928134938527,
"learning_rate": 3.2481665516492876e-06,
"loss": 0.1317,
"step": 819
},
{
"epoch": 1.2293853073463268,
"grad_norm": 1.1988475918746555,
"learning_rate": 3.2371427267486044e-06,
"loss": 0.1246,
"step": 820
},
{
"epoch": 1.2308845577211394,
"grad_norm": 1.275286074409384,
"learning_rate": 3.2261286788349127e-06,
"loss": 0.1634,
"step": 821
},
{
"epoch": 1.232383808095952,
"grad_norm": 1.3995624280447843,
"learning_rate": 3.2151244689932505e-06,
"loss": 0.1488,
"step": 822
},
{
"epoch": 1.2338830584707647,
"grad_norm": 1.4104751467041678,
"learning_rate": 3.2041301582540903e-06,
"loss": 0.1286,
"step": 823
},
{
"epoch": 1.235382308845577,
"grad_norm": 1.2445006734481485,
"learning_rate": 3.1931458075930046e-06,
"loss": 0.1326,
"step": 824
},
{
"epoch": 1.23688155922039,
"grad_norm": 1.1997914952456805,
"learning_rate": 3.182171477930332e-06,
"loss": 0.1398,
"step": 825
},
{
"epoch": 1.2383808095952025,
"grad_norm": 1.1650965283772017,
"learning_rate": 3.171207230130826e-06,
"loss": 0.1245,
"step": 826
},
{
"epoch": 1.239880059970015,
"grad_norm": 1.4224565886835228,
"learning_rate": 3.1602531250033286e-06,
"loss": 0.1441,
"step": 827
},
{
"epoch": 1.2413793103448276,
"grad_norm": 1.3213332823744537,
"learning_rate": 3.149309223300428e-06,
"loss": 0.1373,
"step": 828
},
{
"epoch": 1.2428785607196402,
"grad_norm": 1.3395941381528507,
"learning_rate": 3.1383755857181253e-06,
"loss": 0.1004,
"step": 829
},
{
"epoch": 1.2443778110944528,
"grad_norm": 1.4343202287074748,
"learning_rate": 3.1274522728954928e-06,
"loss": 0.1444,
"step": 830
},
{
"epoch": 1.2458770614692654,
"grad_norm": 1.3805798033233598,
"learning_rate": 3.1165393454143423e-06,
"loss": 0.1176,
"step": 831
},
{
"epoch": 1.247376311844078,
"grad_norm": 1.429797685337231,
"learning_rate": 3.1056368637988876e-06,
"loss": 0.1376,
"step": 832
},
{
"epoch": 1.2488755622188905,
"grad_norm": 1.3184640779280599,
"learning_rate": 3.0947448885154085e-06,
"loss": 0.1052,
"step": 833
},
{
"epoch": 1.250374812593703,
"grad_norm": 1.4125294862634858,
"learning_rate": 3.0838634799719157e-06,
"loss": 0.1762,
"step": 834
},
{
"epoch": 1.2518740629685157,
"grad_norm": 1.399390144522578,
"learning_rate": 3.072992698517815e-06,
"loss": 0.1143,
"step": 835
},
{
"epoch": 1.2533733133433285,
"grad_norm": 1.4083090255847572,
"learning_rate": 3.0621326044435738e-06,
"loss": 0.1733,
"step": 836
},
{
"epoch": 1.2548725637181408,
"grad_norm": 1.484272414476059,
"learning_rate": 3.0512832579803873e-06,
"loss": 0.1402,
"step": 837
},
{
"epoch": 1.2563718140929536,
"grad_norm": 1.3812662927559538,
"learning_rate": 3.0404447192998398e-06,
"loss": 0.1522,
"step": 838
},
{
"epoch": 1.2578710644677662,
"grad_norm": 1.2373359431123467,
"learning_rate": 3.029617048513579e-06,
"loss": 0.0968,
"step": 839
},
{
"epoch": 1.2593703148425788,
"grad_norm": 1.0532358406683526,
"learning_rate": 3.0188003056729752e-06,
"loss": 0.1136,
"step": 840
},
{
"epoch": 1.2608695652173914,
"grad_norm": 1.3370557887300012,
"learning_rate": 3.007994550768793e-06,
"loss": 0.1194,
"step": 841
},
{
"epoch": 1.262368815592204,
"grad_norm": 1.3888773960912888,
"learning_rate": 2.9971998437308546e-06,
"loss": 0.148,
"step": 842
},
{
"epoch": 1.2638680659670165,
"grad_norm": 1.327843448779607,
"learning_rate": 2.9864162444277118e-06,
"loss": 0.1604,
"step": 843
},
{
"epoch": 1.265367316341829,
"grad_norm": 1.6127561280028084,
"learning_rate": 2.97564381266631e-06,
"loss": 0.1344,
"step": 844
},
{
"epoch": 1.2668665667166417,
"grad_norm": 1.150612273649465,
"learning_rate": 2.964882608191659e-06,
"loss": 0.1065,
"step": 845
},
{
"epoch": 1.2683658170914542,
"grad_norm": 1.3198941904967931,
"learning_rate": 2.954132690686502e-06,
"loss": 0.148,
"step": 846
},
{
"epoch": 1.2698650674662668,
"grad_norm": 1.3171201662076748,
"learning_rate": 2.9433941197709813e-06,
"loss": 0.1582,
"step": 847
},
{
"epoch": 1.2713643178410794,
"grad_norm": 1.6640340192874812,
"learning_rate": 2.9326669550023124e-06,
"loss": 0.1527,
"step": 848
},
{
"epoch": 1.272863568215892,
"grad_norm": 1.191103327823784,
"learning_rate": 2.921951255874449e-06,
"loss": 0.0998,
"step": 849
},
{
"epoch": 1.2743628185907045,
"grad_norm": 1.3329297236987123,
"learning_rate": 2.9112470818177563e-06,
"loss": 0.1391,
"step": 850
},
{
"epoch": 1.2758620689655173,
"grad_norm": 1.3806357776189597,
"learning_rate": 2.9005544921986774e-06,
"loss": 0.1674,
"step": 851
},
{
"epoch": 1.2773613193403297,
"grad_norm": 1.316672981264349,
"learning_rate": 2.8898735463194128e-06,
"loss": 0.1288,
"step": 852
},
{
"epoch": 1.2788605697151425,
"grad_norm": 1.389744271741816,
"learning_rate": 2.8792043034175817e-06,
"loss": 0.1648,
"step": 853
},
{
"epoch": 1.280359820089955,
"grad_norm": 1.2804283857478296,
"learning_rate": 2.8685468226658974e-06,
"loss": 0.1478,
"step": 854
},
{
"epoch": 1.2818590704647677,
"grad_norm": 1.3085879349069323,
"learning_rate": 2.85790116317184e-06,
"loss": 0.1291,
"step": 855
},
{
"epoch": 1.2833583208395802,
"grad_norm": 1.1718560022595523,
"learning_rate": 2.8472673839773267e-06,
"loss": 0.1281,
"step": 856
},
{
"epoch": 1.2848575712143928,
"grad_norm": 1.4174010495436282,
"learning_rate": 2.8366455440583874e-06,
"loss": 0.1479,
"step": 857
},
{
"epoch": 1.2863568215892054,
"grad_norm": 1.3701745201308646,
"learning_rate": 2.8260357023248323e-06,
"loss": 0.18,
"step": 858
},
{
"epoch": 1.287856071964018,
"grad_norm": 1.2164522782730773,
"learning_rate": 2.815437917619932e-06,
"loss": 0.1545,
"step": 859
},
{
"epoch": 1.2893553223388305,
"grad_norm": 1.545266209233553,
"learning_rate": 2.804852248720085e-06,
"loss": 0.1508,
"step": 860
},
{
"epoch": 1.2908545727136431,
"grad_norm": 1.178187836068456,
"learning_rate": 2.7942787543344957e-06,
"loss": 0.1646,
"step": 861
},
{
"epoch": 1.2923538230884557,
"grad_norm": 1.2847407117252163,
"learning_rate": 2.783717493104846e-06,
"loss": 0.1311,
"step": 862
},
{
"epoch": 1.2938530734632683,
"grad_norm": 1.2065593565399568,
"learning_rate": 2.7731685236049745e-06,
"loss": 0.186,
"step": 863
},
{
"epoch": 1.295352323838081,
"grad_norm": 1.2537634563394848,
"learning_rate": 2.762631904340546e-06,
"loss": 0.1176,
"step": 864
},
{
"epoch": 1.2968515742128934,
"grad_norm": 1.4572893072304802,
"learning_rate": 2.7521076937487248e-06,
"loss": 0.1374,
"step": 865
},
{
"epoch": 1.2983508245877062,
"grad_norm": 1.1604095621916721,
"learning_rate": 2.7415959501978674e-06,
"loss": 0.1347,
"step": 866
},
{
"epoch": 1.2998500749625188,
"grad_norm": 1.2797788317906116,
"learning_rate": 2.731096731987177e-06,
"loss": 0.1399,
"step": 867
},
{
"epoch": 1.3013493253373314,
"grad_norm": 1.2600649383977571,
"learning_rate": 2.7206100973463958e-06,
"loss": 0.112,
"step": 868
},
{
"epoch": 1.302848575712144,
"grad_norm": 1.3111389852634707,
"learning_rate": 2.71013610443547e-06,
"loss": 0.1498,
"step": 869
},
{
"epoch": 1.3043478260869565,
"grad_norm": 1.283095079431425,
"learning_rate": 2.6996748113442397e-06,
"loss": 0.1495,
"step": 870
},
{
"epoch": 1.3058470764617691,
"grad_norm": 1.2906279291406924,
"learning_rate": 2.689226276092107e-06,
"loss": 0.1546,
"step": 871
},
{
"epoch": 1.3073463268365817,
"grad_norm": 1.37699366581781,
"learning_rate": 2.6787905566277185e-06,
"loss": 0.1963,
"step": 872
},
{
"epoch": 1.3088455772113943,
"grad_norm": 1.267731604106557,
"learning_rate": 2.6683677108286423e-06,
"loss": 0.1407,
"step": 873
},
{
"epoch": 1.3103448275862069,
"grad_norm": 1.3983973615367558,
"learning_rate": 2.65795779650105e-06,
"loss": 0.1407,
"step": 874
},
{
"epoch": 1.3118440779610194,
"grad_norm": 1.2116834320152923,
"learning_rate": 2.6475608713793923e-06,
"loss": 0.1147,
"step": 875
},
{
"epoch": 1.313343328335832,
"grad_norm": 1.2779312117230872,
"learning_rate": 2.6371769931260806e-06,
"loss": 0.1091,
"step": 876
},
{
"epoch": 1.3148425787106448,
"grad_norm": 1.3310728618855927,
"learning_rate": 2.6268062193311672e-06,
"loss": 0.1411,
"step": 877
},
{
"epoch": 1.3163418290854572,
"grad_norm": 1.1705569257005464,
"learning_rate": 2.6164486075120245e-06,
"loss": 0.1245,
"step": 878
},
{
"epoch": 1.31784107946027,
"grad_norm": 1.3341056541286225,
"learning_rate": 2.606104215113033e-06,
"loss": 0.1422,
"step": 879
},
{
"epoch": 1.3193403298350825,
"grad_norm": 1.3024411783557586,
"learning_rate": 2.5957730995052477e-06,
"loss": 0.1339,
"step": 880
},
{
"epoch": 1.3208395802098951,
"grad_norm": 1.0751188596818317,
"learning_rate": 2.585455317986095e-06,
"loss": 0.104,
"step": 881
},
{
"epoch": 1.3223388305847077,
"grad_norm": 1.4384098550039184,
"learning_rate": 2.5751509277790487e-06,
"loss": 0.1949,
"step": 882
},
{
"epoch": 1.3238380809595203,
"grad_norm": 1.3787195214409598,
"learning_rate": 2.5648599860333122e-06,
"loss": 0.1139,
"step": 883
},
{
"epoch": 1.3253373313343328,
"grad_norm": 1.4085530010640945,
"learning_rate": 2.554582549823502e-06,
"loss": 0.1371,
"step": 884
},
{
"epoch": 1.3268365817091454,
"grad_norm": 1.1829924005858234,
"learning_rate": 2.5443186761493327e-06,
"loss": 0.153,
"step": 885
},
{
"epoch": 1.328335832083958,
"grad_norm": 1.2689922518881562,
"learning_rate": 2.5340684219352977e-06,
"loss": 0.143,
"step": 886
},
{
"epoch": 1.3298350824587706,
"grad_norm": 1.4492441219474554,
"learning_rate": 2.523831844030358e-06,
"loss": 0.2237,
"step": 887
},
{
"epoch": 1.3313343328335832,
"grad_norm": 1.3724555732722612,
"learning_rate": 2.513608999207622e-06,
"loss": 0.132,
"step": 888
},
{
"epoch": 1.3328335832083957,
"grad_norm": 1.4409654292658438,
"learning_rate": 2.503399944164035e-06,
"loss": 0.1496,
"step": 889
},
{
"epoch": 1.3343328335832085,
"grad_norm": 1.2353769146697504,
"learning_rate": 2.4932047355200613e-06,
"loss": 0.132,
"step": 890
},
{
"epoch": 1.3358320839580209,
"grad_norm": 1.2911994019209236,
"learning_rate": 2.483023429819372e-06,
"loss": 0.1232,
"step": 891
},
{
"epoch": 1.3373313343328337,
"grad_norm": 1.1296916111789772,
"learning_rate": 2.472856083528531e-06,
"loss": 0.1347,
"step": 892
},
{
"epoch": 1.338830584707646,
"grad_norm": 1.3384892785279934,
"learning_rate": 2.4627027530366836e-06,
"loss": 0.1217,
"step": 893
},
{
"epoch": 1.3403298350824588,
"grad_norm": 1.1990701672887576,
"learning_rate": 2.4525634946552405e-06,
"loss": 0.1367,
"step": 894
},
{
"epoch": 1.3418290854572714,
"grad_norm": 1.6287895885905193,
"learning_rate": 2.442438364617567e-06,
"loss": 0.2167,
"step": 895
},
{
"epoch": 1.343328335832084,
"grad_norm": 1.6320237473460248,
"learning_rate": 2.4323274190786703e-06,
"loss": 0.137,
"step": 896
},
{
"epoch": 1.3448275862068966,
"grad_norm": 1.2070451582386006,
"learning_rate": 2.422230714114891e-06,
"loss": 0.15,
"step": 897
},
{
"epoch": 1.3463268365817092,
"grad_norm": 1.0813044182068166,
"learning_rate": 2.4121483057235884e-06,
"loss": 0.1673,
"step": 898
},
{
"epoch": 1.3478260869565217,
"grad_norm": 1.3765592410946605,
"learning_rate": 2.4020802498228333e-06,
"loss": 0.1423,
"step": 899
},
{
"epoch": 1.3493253373313343,
"grad_norm": 1.0216979685188097,
"learning_rate": 2.392026602251093e-06,
"loss": 0.1097,
"step": 900
},
{
"epoch": 1.3508245877061469,
"grad_norm": 1.395082211672787,
"learning_rate": 2.3819874187669266e-06,
"loss": 0.1498,
"step": 901
},
{
"epoch": 1.3523238380809595,
"grad_norm": 1.2772714877694418,
"learning_rate": 2.371962755048675e-06,
"loss": 0.1439,
"step": 902
},
{
"epoch": 1.353823088455772,
"grad_norm": 1.2230414487038161,
"learning_rate": 2.36195266669415e-06,
"loss": 0.1498,
"step": 903
},
{
"epoch": 1.3553223388305846,
"grad_norm": 1.2133735297762844,
"learning_rate": 2.351957209220326e-06,
"loss": 0.0944,
"step": 904
},
{
"epoch": 1.3568215892053974,
"grad_norm": 1.2730569058592784,
"learning_rate": 2.341976438063035e-06,
"loss": 0.1699,
"step": 905
},
{
"epoch": 1.3583208395802098,
"grad_norm": 1.235232987317895,
"learning_rate": 2.332010408576653e-06,
"loss": 0.1164,
"step": 906
},
{
"epoch": 1.3598200899550226,
"grad_norm": 1.22888641011766,
"learning_rate": 2.3220591760338046e-06,
"loss": 0.1243,
"step": 907
},
{
"epoch": 1.3613193403298351,
"grad_norm": 1.3520510496586944,
"learning_rate": 2.3121227956250435e-06,
"loss": 0.1295,
"step": 908
},
{
"epoch": 1.3628185907046477,
"grad_norm": 1.3900456962266945,
"learning_rate": 2.302201322458552e-06,
"loss": 0.127,
"step": 909
},
{
"epoch": 1.3643178410794603,
"grad_norm": 1.2949158294246113,
"learning_rate": 2.292294811559837e-06,
"loss": 0.135,
"step": 910
},
{
"epoch": 1.3658170914542729,
"grad_norm": 1.2139697429774938,
"learning_rate": 2.282403317871422e-06,
"loss": 0.1253,
"step": 911
},
{
"epoch": 1.3673163418290855,
"grad_norm": 1.31250625327868,
"learning_rate": 2.2725268962525454e-06,
"loss": 0.1663,
"step": 912
},
{
"epoch": 1.368815592203898,
"grad_norm": 1.2681561846101566,
"learning_rate": 2.262665601478852e-06,
"loss": 0.1495,
"step": 913
},
{
"epoch": 1.3703148425787106,
"grad_norm": 1.286221926294528,
"learning_rate": 2.252819488242093e-06,
"loss": 0.1389,
"step": 914
},
{
"epoch": 1.3718140929535232,
"grad_norm": 1.242105773688379,
"learning_rate": 2.24298861114982e-06,
"loss": 0.1304,
"step": 915
},
{
"epoch": 1.3733133433283358,
"grad_norm": 1.1667895987481969,
"learning_rate": 2.2331730247250857e-06,
"loss": 0.1061,
"step": 916
},
{
"epoch": 1.3748125937031483,
"grad_norm": 1.5650235156411083,
"learning_rate": 2.223372783406137e-06,
"loss": 0.1256,
"step": 917
},
{
"epoch": 1.3763118440779611,
"grad_norm": 1.3344433479675109,
"learning_rate": 2.2135879415461152e-06,
"loss": 0.1191,
"step": 918
},
{
"epoch": 1.3778110944527735,
"grad_norm": 1.540334497517668,
"learning_rate": 2.203818553412757e-06,
"loss": 0.1574,
"step": 919
},
{
"epoch": 1.3793103448275863,
"grad_norm": 1.3647654710975659,
"learning_rate": 2.1940646731880887e-06,
"loss": 0.1362,
"step": 920
},
{
"epoch": 1.3808095952023989,
"grad_norm": 1.1167831376180046,
"learning_rate": 2.1843263549681287e-06,
"loss": 0.1465,
"step": 921
},
{
"epoch": 1.3823088455772115,
"grad_norm": 1.2857228281515627,
"learning_rate": 2.174603652762588e-06,
"loss": 0.1224,
"step": 922
},
{
"epoch": 1.383808095952024,
"grad_norm": 1.422505378785925,
"learning_rate": 2.164896620494569e-06,
"loss": 0.1378,
"step": 923
},
{
"epoch": 1.3853073463268366,
"grad_norm": 1.5005035345217537,
"learning_rate": 2.1552053120002655e-06,
"loss": 0.132,
"step": 924
},
{
"epoch": 1.3868065967016492,
"grad_norm": 1.407570214282245,
"learning_rate": 2.145529781028668e-06,
"loss": 0.1133,
"step": 925
},
{
"epoch": 1.3883058470764618,
"grad_norm": 1.0514670390858363,
"learning_rate": 2.1358700812412625e-06,
"loss": 0.1089,
"step": 926
},
{
"epoch": 1.3898050974512743,
"grad_norm": 1.083129668862111,
"learning_rate": 2.1262262662117327e-06,
"loss": 0.1231,
"step": 927
},
{
"epoch": 1.391304347826087,
"grad_norm": 1.299774010899149,
"learning_rate": 2.1165983894256647e-06,
"loss": 0.1235,
"step": 928
},
{
"epoch": 1.3928035982008995,
"grad_norm": 1.6625102293551262,
"learning_rate": 2.1069865042802502e-06,
"loss": 0.1633,
"step": 929
},
{
"epoch": 1.394302848575712,
"grad_norm": 1.4135663597043977,
"learning_rate": 2.0973906640839867e-06,
"loss": 0.1027,
"step": 930
},
{
"epoch": 1.3958020989505249,
"grad_norm": 1.0803337138904263,
"learning_rate": 2.0878109220563884e-06,
"loss": 0.0994,
"step": 931
},
{
"epoch": 1.3973013493253372,
"grad_norm": 1.2267937559800803,
"learning_rate": 2.078247331327685e-06,
"loss": 0.1573,
"step": 932
},
{
"epoch": 1.39880059970015,
"grad_norm": 1.3902432370089108,
"learning_rate": 2.0686999449385286e-06,
"loss": 0.1289,
"step": 933
},
{
"epoch": 1.4002998500749624,
"grad_norm": 1.0727372587178268,
"learning_rate": 2.0591688158397054e-06,
"loss": 0.0882,
"step": 934
},
{
"epoch": 1.4017991004497752,
"grad_norm": 1.2763440022815213,
"learning_rate": 2.0496539968918342e-06,
"loss": 0.1217,
"step": 935
},
{
"epoch": 1.4032983508245878,
"grad_norm": 1.2014108208253573,
"learning_rate": 2.0401555408650714e-06,
"loss": 0.1362,
"step": 936
},
{
"epoch": 1.4047976011994003,
"grad_norm": 1.483112482396683,
"learning_rate": 2.030673500438828e-06,
"loss": 0.1488,
"step": 937
},
{
"epoch": 1.406296851574213,
"grad_norm": 1.1754077343561806,
"learning_rate": 2.0212079282014725e-06,
"loss": 0.1,
"step": 938
},
{
"epoch": 1.4077961019490255,
"grad_norm": 1.2495489419422312,
"learning_rate": 2.0117588766500375e-06,
"loss": 0.1476,
"step": 939
},
{
"epoch": 1.409295352323838,
"grad_norm": 1.4585345367189024,
"learning_rate": 2.002326398189931e-06,
"loss": 0.173,
"step": 940
},
{
"epoch": 1.4107946026986506,
"grad_norm": 1.404097214903437,
"learning_rate": 1.9929105451346436e-06,
"loss": 0.1197,
"step": 941
},
{
"epoch": 1.4122938530734632,
"grad_norm": 1.4538612436978717,
"learning_rate": 1.983511369705462e-06,
"loss": 0.1472,
"step": 942
},
{
"epoch": 1.4137931034482758,
"grad_norm": 1.3822857891996712,
"learning_rate": 1.9741289240311757e-06,
"loss": 0.1259,
"step": 943
},
{
"epoch": 1.4152923538230884,
"grad_norm": 1.274351641557688,
"learning_rate": 1.9647632601477877e-06,
"loss": 0.1524,
"step": 944
},
{
"epoch": 1.416791604197901,
"grad_norm": 1.3817398089545339,
"learning_rate": 1.9554144299982314e-06,
"loss": 0.1502,
"step": 945
},
{
"epoch": 1.4182908545727138,
"grad_norm": 1.301939773768075,
"learning_rate": 1.9460824854320755e-06,
"loss": 0.1301,
"step": 946
},
{
"epoch": 1.419790104947526,
"grad_norm": 1.341452577174406,
"learning_rate": 1.9367674782052376e-06,
"loss": 0.1629,
"step": 947
},
{
"epoch": 1.421289355322339,
"grad_norm": 1.2897360641073317,
"learning_rate": 1.9274694599797067e-06,
"loss": 0.1464,
"step": 948
},
{
"epoch": 1.4227886056971515,
"grad_norm": 1.217713411594433,
"learning_rate": 1.918188482323242e-06,
"loss": 0.1657,
"step": 949
},
{
"epoch": 1.424287856071964,
"grad_norm": 1.265335158791293,
"learning_rate": 1.9089245967090952e-06,
"loss": 0.1304,
"step": 950
},
{
"epoch": 1.4257871064467766,
"grad_norm": 1.2800428877170134,
"learning_rate": 1.8996778545157263e-06,
"loss": 0.1234,
"step": 951
},
{
"epoch": 1.4272863568215892,
"grad_norm": 1.2608530620594376,
"learning_rate": 1.8904483070265133e-06,
"loss": 0.1486,
"step": 952
},
{
"epoch": 1.4287856071964018,
"grad_norm": 1.4554065467824044,
"learning_rate": 1.8812360054294725e-06,
"loss": 0.1381,
"step": 953
},
{
"epoch": 1.4302848575712144,
"grad_norm": 1.3961840817217093,
"learning_rate": 1.8720410008169727e-06,
"loss": 0.1677,
"step": 954
},
{
"epoch": 1.431784107946027,
"grad_norm": 1.4460236341555863,
"learning_rate": 1.8628633441854515e-06,
"loss": 0.239,
"step": 955
},
{
"epoch": 1.4332833583208395,
"grad_norm": 1.4796942546972116,
"learning_rate": 1.8537030864351303e-06,
"loss": 0.1566,
"step": 956
},
{
"epoch": 1.434782608695652,
"grad_norm": 1.1462880365324495,
"learning_rate": 1.8445602783697375e-06,
"loss": 0.1321,
"step": 957
},
{
"epoch": 1.4362818590704647,
"grad_norm": 1.585283738421672,
"learning_rate": 1.8354349706962243e-06,
"loss": 0.1272,
"step": 958
},
{
"epoch": 1.4377811094452775,
"grad_norm": 1.0494214298183657,
"learning_rate": 1.8263272140244803e-06,
"loss": 0.1376,
"step": 959
},
{
"epoch": 1.4392803598200898,
"grad_norm": 1.2543649534654184,
"learning_rate": 1.8172370588670563e-06,
"loss": 0.1329,
"step": 960
},
{
"epoch": 1.4407796101949026,
"grad_norm": 1.4256311901440206,
"learning_rate": 1.8081645556388866e-06,
"loss": 0.1269,
"step": 961
},
{
"epoch": 1.4422788605697152,
"grad_norm": 1.2745005154484748,
"learning_rate": 1.7991097546570018e-06,
"loss": 0.1372,
"step": 962
},
{
"epoch": 1.4437781109445278,
"grad_norm": 1.3767502833369671,
"learning_rate": 1.7900727061402556e-06,
"loss": 0.1623,
"step": 963
},
{
"epoch": 1.4452773613193404,
"grad_norm": 1.473223666102311,
"learning_rate": 1.7810534602090445e-06,
"loss": 0.1244,
"step": 964
},
{
"epoch": 1.446776611694153,
"grad_norm": 1.5980102374273573,
"learning_rate": 1.77205206688503e-06,
"loss": 0.1418,
"step": 965
},
{
"epoch": 1.4482758620689655,
"grad_norm": 1.436451939783491,
"learning_rate": 1.7630685760908623e-06,
"loss": 0.1617,
"step": 966
},
{
"epoch": 1.449775112443778,
"grad_norm": 1.1622192875909254,
"learning_rate": 1.7541030376499002e-06,
"loss": 0.1203,
"step": 967
},
{
"epoch": 1.4512743628185907,
"grad_norm": 1.242253196158236,
"learning_rate": 1.745155501285939e-06,
"loss": 0.1481,
"step": 968
},
{
"epoch": 1.4527736131934033,
"grad_norm": 0.9974964391775575,
"learning_rate": 1.736226016622931e-06,
"loss": 0.1195,
"step": 969
},
{
"epoch": 1.4542728635682158,
"grad_norm": 1.5144900300867414,
"learning_rate": 1.727314633184714e-06,
"loss": 0.1838,
"step": 970
},
{
"epoch": 1.4557721139430284,
"grad_norm": 1.5131114078926966,
"learning_rate": 1.718421400394732e-06,
"loss": 0.1545,
"step": 971
},
{
"epoch": 1.4572713643178412,
"grad_norm": 1.379064276190616,
"learning_rate": 1.7095463675757656e-06,
"loss": 0.1468,
"step": 972
},
{
"epoch": 1.4587706146926536,
"grad_norm": 1.2722713450492789,
"learning_rate": 1.7006895839496557e-06,
"loss": 0.112,
"step": 973
},
{
"epoch": 1.4602698650674664,
"grad_norm": 1.3462576427240196,
"learning_rate": 1.6918510986370312e-06,
"loss": 0.1277,
"step": 974
},
{
"epoch": 1.461769115442279,
"grad_norm": 1.2903840705144083,
"learning_rate": 1.6830309606570372e-06,
"loss": 0.1272,
"step": 975
},
{
"epoch": 1.4632683658170915,
"grad_norm": 1.1343447342988313,
"learning_rate": 1.674229218927062e-06,
"loss": 0.0901,
"step": 976
},
{
"epoch": 1.464767616191904,
"grad_norm": 1.311434924925221,
"learning_rate": 1.665445922262467e-06,
"loss": 0.1323,
"step": 977
},
{
"epoch": 1.4662668665667167,
"grad_norm": 1.526283168070267,
"learning_rate": 1.6566811193763149e-06,
"loss": 0.1317,
"step": 978
},
{
"epoch": 1.4677661169415293,
"grad_norm": 1.189720713308383,
"learning_rate": 1.6479348588791e-06,
"loss": 0.1391,
"step": 979
},
{
"epoch": 1.4692653673163418,
"grad_norm": 1.3157965259486535,
"learning_rate": 1.6392071892784789e-06,
"loss": 0.1479,
"step": 980
},
{
"epoch": 1.4707646176911544,
"grad_norm": 1.0767318615446795,
"learning_rate": 1.6304981589790015e-06,
"loss": 0.1084,
"step": 981
},
{
"epoch": 1.472263868065967,
"grad_norm": 1.3638725536330354,
"learning_rate": 1.6218078162818418e-06,
"loss": 0.1587,
"step": 982
},
{
"epoch": 1.4737631184407796,
"grad_norm": 1.1551897396850164,
"learning_rate": 1.6131362093845299e-06,
"loss": 0.1418,
"step": 983
},
{
"epoch": 1.4752623688155921,
"grad_norm": 1.35859763625055,
"learning_rate": 1.6044833863806864e-06,
"loss": 0.1794,
"step": 984
},
{
"epoch": 1.4767616191904047,
"grad_norm": 1.0886322531605184,
"learning_rate": 1.5958493952597536e-06,
"loss": 0.1328,
"step": 985
},
{
"epoch": 1.4782608695652173,
"grad_norm": 1.1042469830014725,
"learning_rate": 1.5872342839067305e-06,
"loss": 0.1304,
"step": 986
},
{
"epoch": 1.47976011994003,
"grad_norm": 1.4521417610192422,
"learning_rate": 1.5786381001019052e-06,
"loss": 0.1316,
"step": 987
},
{
"epoch": 1.4812593703148424,
"grad_norm": 1.302024189367588,
"learning_rate": 1.5700608915205978e-06,
"loss": 0.1179,
"step": 988
},
{
"epoch": 1.4827586206896552,
"grad_norm": 1.2796658409150223,
"learning_rate": 1.561502705732883e-06,
"loss": 0.1312,
"step": 989
},
{
"epoch": 1.4842578710644678,
"grad_norm": 1.0892145988605106,
"learning_rate": 1.5529635902033358e-06,
"loss": 0.1061,
"step": 990
},
{
"epoch": 1.4857571214392804,
"grad_norm": 1.6080688773455982,
"learning_rate": 1.5444435922907669e-06,
"loss": 0.1238,
"step": 991
},
{
"epoch": 1.487256371814093,
"grad_norm": 1.2356347617084416,
"learning_rate": 1.5359427592479553e-06,
"loss": 0.1576,
"step": 992
},
{
"epoch": 1.4887556221889056,
"grad_norm": 1.4590865482376132,
"learning_rate": 1.5274611382213922e-06,
"loss": 0.1399,
"step": 993
},
{
"epoch": 1.4902548725637181,
"grad_norm": 1.473630114777543,
"learning_rate": 1.5189987762510167e-06,
"loss": 0.1204,
"step": 994
},
{
"epoch": 1.4917541229385307,
"grad_norm": 1.118155590669407,
"learning_rate": 1.510555720269955e-06,
"loss": 0.0941,
"step": 995
},
{
"epoch": 1.4932533733133433,
"grad_norm": 1.3062420399627814,
"learning_rate": 1.5021320171042608e-06,
"loss": 0.1606,
"step": 996
},
{
"epoch": 1.4947526236881559,
"grad_norm": 1.4905042557752983,
"learning_rate": 1.4937277134726542e-06,
"loss": 0.1319,
"step": 997
},
{
"epoch": 1.4962518740629684,
"grad_norm": 1.1349672110630278,
"learning_rate": 1.4853428559862637e-06,
"loss": 0.1272,
"step": 998
},
{
"epoch": 1.497751124437781,
"grad_norm": 1.3077408881003898,
"learning_rate": 1.4769774911483686e-06,
"loss": 0.1553,
"step": 999
},
{
"epoch": 1.4992503748125938,
"grad_norm": 1.3585683981092074,
"learning_rate": 1.4686316653541377e-06,
"loss": 0.1367,
"step": 1000
},
{
"epoch": 1.4992503748125938,
"eval_loss": 0.3032159209251404,
"eval_runtime": 9.5349,
"eval_samples_per_second": 5.663,
"eval_steps_per_second": 1.468,
"step": 1000
},
{
"epoch": 1.5007496251874062,
"grad_norm": 1.2661008032372718,
"learning_rate": 1.4603054248903752e-06,
"loss": 0.1626,
"step": 1001
},
{
"epoch": 1.502248875562219,
"grad_norm": 1.2527278060860814,
"learning_rate": 1.4519988159352665e-06,
"loss": 0.1285,
"step": 1002
},
{
"epoch": 1.5037481259370313,
"grad_norm": 1.421893532069344,
"learning_rate": 1.4437118845581138e-06,
"loss": 0.1347,
"step": 1003
},
{
"epoch": 1.5052473763118441,
"grad_norm": 1.2658713398673795,
"learning_rate": 1.4354446767190873e-06,
"loss": 0.1332,
"step": 1004
},
{
"epoch": 1.5067466266866567,
"grad_norm": 1.4000848731838256,
"learning_rate": 1.4271972382689685e-06,
"loss": 0.1238,
"step": 1005
},
{
"epoch": 1.5082458770614693,
"grad_norm": 1.2285414640269432,
"learning_rate": 1.4189696149488956e-06,
"loss": 0.1363,
"step": 1006
},
{
"epoch": 1.5097451274362819,
"grad_norm": 1.2773344151550985,
"learning_rate": 1.4107618523901101e-06,
"loss": 0.106,
"step": 1007
},
{
"epoch": 1.5112443778110944,
"grad_norm": 1.2601199100453082,
"learning_rate": 1.4025739961137043e-06,
"loss": 0.1426,
"step": 1008
},
{
"epoch": 1.512743628185907,
"grad_norm": 1.3727548879157994,
"learning_rate": 1.394406091530367e-06,
"loss": 0.1121,
"step": 1009
},
{
"epoch": 1.5142428785607196,
"grad_norm": 1.608607894401084,
"learning_rate": 1.3862581839401346e-06,
"loss": 0.1828,
"step": 1010
},
{
"epoch": 1.5157421289355324,
"grad_norm": 1.124663845902527,
"learning_rate": 1.3781303185321377e-06,
"loss": 0.0926,
"step": 1011
},
{
"epoch": 1.5172413793103448,
"grad_norm": 1.4143041849227191,
"learning_rate": 1.370022540384347e-06,
"loss": 0.1198,
"step": 1012
},
{
"epoch": 1.5187406296851576,
"grad_norm": 1.465343721555682,
"learning_rate": 1.3619348944633331e-06,
"loss": 0.13,
"step": 1013
},
{
"epoch": 1.52023988005997,
"grad_norm": 1.2447895534989184,
"learning_rate": 1.3538674256240087e-06,
"loss": 0.1598,
"step": 1014
},
{
"epoch": 1.5217391304347827,
"grad_norm": 1.4549885776820828,
"learning_rate": 1.3458201786093795e-06,
"loss": 0.1311,
"step": 1015
},
{
"epoch": 1.523238380809595,
"grad_norm": 1.6439292468977473,
"learning_rate": 1.3377931980503055e-06,
"loss": 0.2007,
"step": 1016
},
{
"epoch": 1.5247376311844079,
"grad_norm": 0.962127176393376,
"learning_rate": 1.3297865284652417e-06,
"loss": 0.1067,
"step": 1017
},
{
"epoch": 1.5262368815592204,
"grad_norm": 1.3137271098928553,
"learning_rate": 1.3218002142599973e-06,
"loss": 0.1387,
"step": 1018
},
{
"epoch": 1.527736131934033,
"grad_norm": 1.251568110368441,
"learning_rate": 1.3138342997274883e-06,
"loss": 0.1381,
"step": 1019
},
{
"epoch": 1.5292353823088456,
"grad_norm": 1.133675448250836,
"learning_rate": 1.3058888290474937e-06,
"loss": 0.1027,
"step": 1020
},
{
"epoch": 1.5307346326836582,
"grad_norm": 1.427729760250351,
"learning_rate": 1.2979638462864069e-06,
"loss": 0.1216,
"step": 1021
},
{
"epoch": 1.5322338830584707,
"grad_norm": 1.4613681322730085,
"learning_rate": 1.2900593953969947e-06,
"loss": 0.1243,
"step": 1022
},
{
"epoch": 1.5337331334332833,
"grad_norm": 1.3020393066845384,
"learning_rate": 1.2821755202181503e-06,
"loss": 0.1196,
"step": 1023
},
{
"epoch": 1.535232383808096,
"grad_norm": 1.4126438396486742,
"learning_rate": 1.2743122644746536e-06,
"loss": 0.1717,
"step": 1024
},
{
"epoch": 1.5367316341829085,
"grad_norm": 1.3487856526588313,
"learning_rate": 1.266469671776926e-06,
"loss": 0.1239,
"step": 1025
},
{
"epoch": 1.5382308845577213,
"grad_norm": 1.6582962090055022,
"learning_rate": 1.2586477856207902e-06,
"loss": 0.1776,
"step": 1026
},
{
"epoch": 1.5397301349325336,
"grad_norm": 1.3304439720565826,
"learning_rate": 1.2508466493872273e-06,
"loss": 0.1339,
"step": 1027
},
{
"epoch": 1.5412293853073464,
"grad_norm": 1.3715694584706903,
"learning_rate": 1.2430663063421388e-06,
"loss": 0.1274,
"step": 1028
},
{
"epoch": 1.5427286356821588,
"grad_norm": 1.352084074067662,
"learning_rate": 1.2353067996361034e-06,
"loss": 0.1363,
"step": 1029
},
{
"epoch": 1.5442278860569716,
"grad_norm": 1.3830141716551954,
"learning_rate": 1.2275681723041406e-06,
"loss": 0.1137,
"step": 1030
},
{
"epoch": 1.545727136431784,
"grad_norm": 1.2865850156180865,
"learning_rate": 1.2198504672654694e-06,
"loss": 0.1134,
"step": 1031
},
{
"epoch": 1.5472263868065967,
"grad_norm": 1.0607156398556805,
"learning_rate": 1.212153727323273e-06,
"loss": 0.1133,
"step": 1032
},
{
"epoch": 1.5487256371814093,
"grad_norm": 1.1884021672187197,
"learning_rate": 1.2044779951644586e-06,
"loss": 0.1321,
"step": 1033
},
{
"epoch": 1.550224887556222,
"grad_norm": 1.5194385658530858,
"learning_rate": 1.1968233133594243e-06,
"loss": 0.1243,
"step": 1034
},
{
"epoch": 1.5517241379310345,
"grad_norm": 1.1891807656263866,
"learning_rate": 1.1891897243618184e-06,
"loss": 0.122,
"step": 1035
},
{
"epoch": 1.553223388305847,
"grad_norm": 1.4329929737293103,
"learning_rate": 1.1815772705083072e-06,
"loss": 0.116,
"step": 1036
},
{
"epoch": 1.5547226386806596,
"grad_norm": 1.3786502166630517,
"learning_rate": 1.17398599401834e-06,
"loss": 0.1462,
"step": 1037
},
{
"epoch": 1.5562218890554722,
"grad_norm": 1.2776143515250926,
"learning_rate": 1.1664159369939137e-06,
"loss": 0.1343,
"step": 1038
},
{
"epoch": 1.557721139430285,
"grad_norm": 1.4095443161123418,
"learning_rate": 1.1588671414193397e-06,
"loss": 0.14,
"step": 1039
},
{
"epoch": 1.5592203898050974,
"grad_norm": 1.4162615793126077,
"learning_rate": 1.1513396491610113e-06,
"loss": 0.1125,
"step": 1040
},
{
"epoch": 1.5607196401799102,
"grad_norm": 1.2350782947306302,
"learning_rate": 1.1438335019671715e-06,
"loss": 0.0998,
"step": 1041
},
{
"epoch": 1.5622188905547225,
"grad_norm": 1.4531486845257424,
"learning_rate": 1.1363487414676805e-06,
"loss": 0.13,
"step": 1042
},
{
"epoch": 1.5637181409295353,
"grad_norm": 1.4173618779997708,
"learning_rate": 1.128885409173789e-06,
"loss": 0.1394,
"step": 1043
},
{
"epoch": 1.5652173913043477,
"grad_norm": 1.2755844414820892,
"learning_rate": 1.1214435464779006e-06,
"loss": 0.1396,
"step": 1044
},
{
"epoch": 1.5667166416791605,
"grad_norm": 1.3708803915954113,
"learning_rate": 1.1140231946533486e-06,
"loss": 0.1215,
"step": 1045
},
{
"epoch": 1.568215892053973,
"grad_norm": 1.381903217425136,
"learning_rate": 1.1066243948541638e-06,
"loss": 0.132,
"step": 1046
},
{
"epoch": 1.5697151424287856,
"grad_norm": 1.3791377921791983,
"learning_rate": 1.0992471881148497e-06,
"loss": 0.1597,
"step": 1047
},
{
"epoch": 1.5712143928035982,
"grad_norm": 1.4041721910528315,
"learning_rate": 1.091891615350147e-06,
"loss": 0.1397,
"step": 1048
},
{
"epoch": 1.5727136431784108,
"grad_norm": 1.3682651227412774,
"learning_rate": 1.0845577173548172e-06,
"loss": 0.136,
"step": 1049
},
{
"epoch": 1.5742128935532234,
"grad_norm": 1.2250049124228923,
"learning_rate": 1.07724553480341e-06,
"loss": 0.121,
"step": 1050
},
{
"epoch": 1.575712143928036,
"grad_norm": 1.3605511160908002,
"learning_rate": 1.0699551082500387e-06,
"loss": 0.104,
"step": 1051
},
{
"epoch": 1.5772113943028487,
"grad_norm": 1.481884448847055,
"learning_rate": 1.0626864781281553e-06,
"loss": 0.1182,
"step": 1052
},
{
"epoch": 1.578710644677661,
"grad_norm": 1.3519687795217226,
"learning_rate": 1.0554396847503272e-06,
"loss": 0.1148,
"step": 1053
},
{
"epoch": 1.580209895052474,
"grad_norm": 1.3696262077208985,
"learning_rate": 1.0482147683080125e-06,
"loss": 0.1666,
"step": 1054
},
{
"epoch": 1.5817091454272862,
"grad_norm": 1.205147099427604,
"learning_rate": 1.0410117688713366e-06,
"loss": 0.1447,
"step": 1055
},
{
"epoch": 1.583208395802099,
"grad_norm": 1.4584035383495035,
"learning_rate": 1.0338307263888748e-06,
"loss": 0.126,
"step": 1056
},
{
"epoch": 1.5847076461769114,
"grad_norm": 1.2806511365390885,
"learning_rate": 1.0266716806874227e-06,
"loss": 0.1706,
"step": 1057
},
{
"epoch": 1.5862068965517242,
"grad_norm": 1.2292034261665328,
"learning_rate": 1.0195346714717813e-06,
"loss": 0.1351,
"step": 1058
},
{
"epoch": 1.5877061469265368,
"grad_norm": 1.2746750602503882,
"learning_rate": 1.0124197383245344e-06,
"loss": 0.1262,
"step": 1059
},
{
"epoch": 1.5892053973013494,
"grad_norm": 1.1466214924152243,
"learning_rate": 1.0053269207058298e-06,
"loss": 0.1016,
"step": 1060
},
{
"epoch": 1.590704647676162,
"grad_norm": 1.2990048736912905,
"learning_rate": 9.982562579531607e-07,
"loss": 0.1346,
"step": 1061
},
{
"epoch": 1.5922038980509745,
"grad_norm": 1.2500168676615038,
"learning_rate": 9.912077892811473e-07,
"loss": 0.086,
"step": 1062
},
{
"epoch": 1.593703148425787,
"grad_norm": 1.3221455765209738,
"learning_rate": 9.841815537813177e-07,
"loss": 0.1057,
"step": 1063
},
{
"epoch": 1.5952023988005997,
"grad_norm": 1.6581000106094772,
"learning_rate": 9.77177590421895e-07,
"loss": 0.1193,
"step": 1064
},
{
"epoch": 1.5967016491754122,
"grad_norm": 1.5238839036341836,
"learning_rate": 9.70195938047576e-07,
"loss": 0.181,
"step": 1065
},
{
"epoch": 1.5982008995502248,
"grad_norm": 1.369641755583762,
"learning_rate": 9.63236635379321e-07,
"loss": 0.1193,
"step": 1066
},
{
"epoch": 1.5997001499250376,
"grad_norm": 1.5315504387546468,
"learning_rate": 9.562997210141355e-07,
"loss": 0.1229,
"step": 1067
},
{
"epoch": 1.60119940029985,
"grad_norm": 1.395503826008592,
"learning_rate": 9.49385233424856e-07,
"loss": 0.1275,
"step": 1068
},
{
"epoch": 1.6026986506746628,
"grad_norm": 1.2596162129099466,
"learning_rate": 9.424932109599372e-07,
"loss": 0.1301,
"step": 1069
},
{
"epoch": 1.6041979010494751,
"grad_norm": 1.3401982239935306,
"learning_rate": 9.356236918432454e-07,
"loss": 0.1389,
"step": 1070
},
{
"epoch": 1.605697151424288,
"grad_norm": 1.3134889012190543,
"learning_rate": 9.287767141738352e-07,
"loss": 0.1498,
"step": 1071
},
{
"epoch": 1.6071964017991005,
"grad_norm": 1.283193424293543,
"learning_rate": 9.21952315925746e-07,
"loss": 0.1265,
"step": 1072
},
{
"epoch": 1.608695652173913,
"grad_norm": 1.465380366009575,
"learning_rate": 9.151505349477901e-07,
"loss": 0.1305,
"step": 1073
},
{
"epoch": 1.6101949025487257,
"grad_norm": 1.1719550376703987,
"learning_rate": 9.08371408963341e-07,
"loss": 0.1288,
"step": 1074
},
{
"epoch": 1.6116941529235382,
"grad_norm": 1.3625101567419093,
"learning_rate": 9.016149755701259e-07,
"loss": 0.1471,
"step": 1075
},
{
"epoch": 1.6131934032983508,
"grad_norm": 1.2156667519976243,
"learning_rate": 8.948812722400157e-07,
"loss": 0.1249,
"step": 1076
},
{
"epoch": 1.6146926536731634,
"grad_norm": 1.278558660591185,
"learning_rate": 8.881703363188199e-07,
"loss": 0.1266,
"step": 1077
},
{
"epoch": 1.616191904047976,
"grad_norm": 1.0173628486181656,
"learning_rate": 8.814822050260758e-07,
"loss": 0.1079,
"step": 1078
},
{
"epoch": 1.6176911544227885,
"grad_norm": 1.101628767399371,
"learning_rate": 8.748169154548448e-07,
"loss": 0.0958,
"step": 1079
},
{
"epoch": 1.6191904047976013,
"grad_norm": 1.182084523674803,
"learning_rate": 8.681745045715045e-07,
"loss": 0.1461,
"step": 1080
},
{
"epoch": 1.6206896551724137,
"grad_norm": 1.0002020828857712,
"learning_rate": 8.615550092155478e-07,
"loss": 0.1115,
"step": 1081
},
{
"epoch": 1.6221889055472265,
"grad_norm": 1.4678927852677748,
"learning_rate": 8.549584660993726e-07,
"loss": 0.1203,
"step": 1082
},
{
"epoch": 1.6236881559220389,
"grad_norm": 1.6501694564018676,
"learning_rate": 8.483849118080828e-07,
"loss": 0.1274,
"step": 1083
},
{
"epoch": 1.6251874062968517,
"grad_norm": 1.267755170361984,
"learning_rate": 8.418343827992842e-07,
"loss": 0.1276,
"step": 1084
},
{
"epoch": 1.626686656671664,
"grad_norm": 1.272826311386756,
"learning_rate": 8.353069154028814e-07,
"loss": 0.115,
"step": 1085
},
{
"epoch": 1.6281859070464768,
"grad_norm": 1.4121584145458737,
"learning_rate": 8.28802545820877e-07,
"loss": 0.1449,
"step": 1086
},
{
"epoch": 1.6296851574212894,
"grad_norm": 1.7533318445061865,
"learning_rate": 8.223213101271709e-07,
"loss": 0.1563,
"step": 1087
},
{
"epoch": 1.631184407796102,
"grad_norm": 1.3578821404795234,
"learning_rate": 8.158632442673603e-07,
"loss": 0.1418,
"step": 1088
},
{
"epoch": 1.6326836581709145,
"grad_norm": 1.3372173188024898,
"learning_rate": 8.094283840585398e-07,
"loss": 0.16,
"step": 1089
},
{
"epoch": 1.6341829085457271,
"grad_norm": 1.076968453210384,
"learning_rate": 8.03016765189103e-07,
"loss": 0.1023,
"step": 1090
},
{
"epoch": 1.6356821589205397,
"grad_norm": 1.2173029006222529,
"learning_rate": 7.966284232185451e-07,
"loss": 0.1052,
"step": 1091
},
{
"epoch": 1.6371814092953523,
"grad_norm": 1.4378038164667921,
"learning_rate": 7.902633935772647e-07,
"loss": 0.1468,
"step": 1092
},
{
"epoch": 1.638680659670165,
"grad_norm": 1.513512766949661,
"learning_rate": 7.839217115663683e-07,
"loss": 0.1228,
"step": 1093
},
{
"epoch": 1.6401799100449774,
"grad_norm": 1.6017858779664627,
"learning_rate": 7.776034123574738e-07,
"loss": 0.1795,
"step": 1094
},
{
"epoch": 1.6416791604197902,
"grad_norm": 1.353882475612432,
"learning_rate": 7.713085309925156e-07,
"loss": 0.1381,
"step": 1095
},
{
"epoch": 1.6431784107946026,
"grad_norm": 1.2860764537774483,
"learning_rate": 7.650371023835495e-07,
"loss": 0.1109,
"step": 1096
},
{
"epoch": 1.6446776611694154,
"grad_norm": 1.371159100025601,
"learning_rate": 7.587891613125631e-07,
"loss": 0.155,
"step": 1097
},
{
"epoch": 1.6461769115442277,
"grad_norm": 1.3046289248555103,
"learning_rate": 7.525647424312766e-07,
"loss": 0.116,
"step": 1098
},
{
"epoch": 1.6476761619190405,
"grad_norm": 1.4562702726888381,
"learning_rate": 7.46363880260954e-07,
"loss": 0.1475,
"step": 1099
},
{
"epoch": 1.6491754122938531,
"grad_norm": 1.4285731527144614,
"learning_rate": 7.401866091922133e-07,
"loss": 0.1265,
"step": 1100
},
{
"epoch": 1.6506746626686657,
"grad_norm": 1.1683215451669453,
"learning_rate": 7.340329634848309e-07,
"loss": 0.15,
"step": 1101
},
{
"epoch": 1.6521739130434783,
"grad_norm": 1.320313350640812,
"learning_rate": 7.279029772675572e-07,
"loss": 0.1448,
"step": 1102
},
{
"epoch": 1.6536731634182908,
"grad_norm": 1.188034434280782,
"learning_rate": 7.217966845379243e-07,
"loss": 0.1052,
"step": 1103
},
{
"epoch": 1.6551724137931034,
"grad_norm": 1.3829494559931743,
"learning_rate": 7.157141191620548e-07,
"loss": 0.156,
"step": 1104
},
{
"epoch": 1.656671664167916,
"grad_norm": 1.2764316757400505,
"learning_rate": 7.096553148744806e-07,
"loss": 0.1318,
"step": 1105
},
{
"epoch": 1.6581709145427288,
"grad_norm": 1.400209913228982,
"learning_rate": 7.036203052779506e-07,
"loss": 0.1435,
"step": 1106
},
{
"epoch": 1.6596701649175412,
"grad_norm": 1.3513499085792917,
"learning_rate": 6.97609123843247e-07,
"loss": 0.1202,
"step": 1107
},
{
"epoch": 1.661169415292354,
"grad_norm": 1.3267222518322797,
"learning_rate": 6.916218039089961e-07,
"loss": 0.1279,
"step": 1108
},
{
"epoch": 1.6626686656671663,
"grad_norm": 1.4957467373452389,
"learning_rate": 6.856583786814891e-07,
"loss": 0.1496,
"step": 1109
},
{
"epoch": 1.6641679160419791,
"grad_norm": 1.2849640190193239,
"learning_rate": 6.797188812344907e-07,
"loss": 0.1854,
"step": 1110
},
{
"epoch": 1.6656671664167915,
"grad_norm": 1.2863856936453388,
"learning_rate": 6.738033445090653e-07,
"loss": 0.1224,
"step": 1111
},
{
"epoch": 1.6671664167916043,
"grad_norm": 1.116065369198763,
"learning_rate": 6.67911801313384e-07,
"loss": 0.0949,
"step": 1112
},
{
"epoch": 1.6686656671664168,
"grad_norm": 1.2505299798028895,
"learning_rate": 6.620442843225483e-07,
"loss": 0.141,
"step": 1113
},
{
"epoch": 1.6701649175412294,
"grad_norm": 1.3823124383673955,
"learning_rate": 6.562008260784092e-07,
"loss": 0.0966,
"step": 1114
},
{
"epoch": 1.671664167916042,
"grad_norm": 1.4570716508838586,
"learning_rate": 6.503814589893836e-07,
"loss": 0.1669,
"step": 1115
},
{
"epoch": 1.6731634182908546,
"grad_norm": 1.3226759106524308,
"learning_rate": 6.445862153302784e-07,
"loss": 0.1132,
"step": 1116
},
{
"epoch": 1.6746626686656672,
"grad_norm": 1.2470088426875263,
"learning_rate": 6.388151272421078e-07,
"loss": 0.1208,
"step": 1117
},
{
"epoch": 1.6761619190404797,
"grad_norm": 1.125981550475647,
"learning_rate": 6.330682267319177e-07,
"loss": 0.1513,
"step": 1118
},
{
"epoch": 1.6776611694152923,
"grad_norm": 1.3156942222993357,
"learning_rate": 6.273455456726074e-07,
"loss": 0.1332,
"step": 1119
},
{
"epoch": 1.6791604197901049,
"grad_norm": 1.2148234797505764,
"learning_rate": 6.216471158027515e-07,
"loss": 0.1642,
"step": 1120
},
{
"epoch": 1.6806596701649177,
"grad_norm": 1.2628856491538,
"learning_rate": 6.159729687264254e-07,
"loss": 0.1057,
"step": 1121
},
{
"epoch": 1.68215892053973,
"grad_norm": 1.347516602837082,
"learning_rate": 6.103231359130308e-07,
"loss": 0.1365,
"step": 1122
},
{
"epoch": 1.6836581709145428,
"grad_norm": 1.2777682806438089,
"learning_rate": 6.046976486971201e-07,
"loss": 0.133,
"step": 1123
},
{
"epoch": 1.6851574212893552,
"grad_norm": 1.3288086131013543,
"learning_rate": 5.990965382782177e-07,
"loss": 0.0921,
"step": 1124
},
{
"epoch": 1.686656671664168,
"grad_norm": 1.3733724757973855,
"learning_rate": 5.935198357206595e-07,
"loss": 0.1308,
"step": 1125
},
{
"epoch": 1.6881559220389803,
"grad_norm": 1.3339521765297506,
"learning_rate": 5.879675719534078e-07,
"loss": 0.1465,
"step": 1126
},
{
"epoch": 1.6896551724137931,
"grad_norm": 1.292382820504901,
"learning_rate": 5.824397777698859e-07,
"loss": 0.125,
"step": 1127
},
{
"epoch": 1.6911544227886057,
"grad_norm": 1.3236571388254093,
"learning_rate": 5.769364838278063e-07,
"loss": 0.0991,
"step": 1128
},
{
"epoch": 1.6926536731634183,
"grad_norm": 1.5554875035316833,
"learning_rate": 5.714577206490018e-07,
"loss": 0.1242,
"step": 1129
},
{
"epoch": 1.6941529235382309,
"grad_norm": 1.3881173923805235,
"learning_rate": 5.660035186192531e-07,
"loss": 0.1407,
"step": 1130
},
{
"epoch": 1.6956521739130435,
"grad_norm": 1.313045644845594,
"learning_rate": 5.60573907988124e-07,
"loss": 0.127,
"step": 1131
},
{
"epoch": 1.697151424287856,
"grad_norm": 1.2847529308733094,
"learning_rate": 5.551689188687909e-07,
"loss": 0.1258,
"step": 1132
},
{
"epoch": 1.6986506746626686,
"grad_norm": 1.1567921694342085,
"learning_rate": 5.497885812378772e-07,
"loss": 0.1231,
"step": 1133
},
{
"epoch": 1.7001499250374814,
"grad_norm": 1.0569442318571898,
"learning_rate": 5.444329249352859e-07,
"loss": 0.1302,
"step": 1134
},
{
"epoch": 1.7016491754122938,
"grad_norm": 1.4537474571069005,
"learning_rate": 5.391019796640362e-07,
"loss": 0.0996,
"step": 1135
},
{
"epoch": 1.7031484257871066,
"grad_norm": 1.272211223666709,
"learning_rate": 5.337957749900958e-07,
"loss": 0.1307,
"step": 1136
},
{
"epoch": 1.704647676161919,
"grad_norm": 1.5860743854589014,
"learning_rate": 5.285143403422188e-07,
"loss": 0.176,
"step": 1137
},
{
"epoch": 1.7061469265367317,
"grad_norm": 1.2536957174595447,
"learning_rate": 5.23257705011786e-07,
"loss": 0.1407,
"step": 1138
},
{
"epoch": 1.707646176911544,
"grad_norm": 1.3218941411911886,
"learning_rate": 5.18025898152631e-07,
"loss": 0.1323,
"step": 1139
},
{
"epoch": 1.7091454272863569,
"grad_norm": 1.099502884099189,
"learning_rate": 5.128189487808927e-07,
"loss": 0.0775,
"step": 1140
},
{
"epoch": 1.7106446776611695,
"grad_norm": 1.3524965441592864,
"learning_rate": 5.076368857748454e-07,
"loss": 0.1393,
"step": 1141
},
{
"epoch": 1.712143928035982,
"grad_norm": 1.1455115884594511,
"learning_rate": 5.024797378747414e-07,
"loss": 0.1277,
"step": 1142
},
{
"epoch": 1.7136431784107946,
"grad_norm": 1.4565444265315184,
"learning_rate": 4.973475336826506e-07,
"loss": 0.1618,
"step": 1143
},
{
"epoch": 1.7151424287856072,
"grad_norm": 1.1728745490338242,
"learning_rate": 4.922403016623034e-07,
"loss": 0.1111,
"step": 1144
},
{
"epoch": 1.7166416791604198,
"grad_norm": 1.2809261476992506,
"learning_rate": 4.871580701389316e-07,
"loss": 0.1023,
"step": 1145
},
{
"epoch": 1.7181409295352323,
"grad_norm": 1.304906550454027,
"learning_rate": 4.821008672991118e-07,
"loss": 0.1384,
"step": 1146
},
{
"epoch": 1.7196401799100451,
"grad_norm": 1.4735356913064952,
"learning_rate": 4.770687211906089e-07,
"loss": 0.1393,
"step": 1147
},
{
"epoch": 1.7211394302848575,
"grad_norm": 1.3026231966975248,
"learning_rate": 4.720616597222205e-07,
"loss": 0.1079,
"step": 1148
},
{
"epoch": 1.7226386806596703,
"grad_norm": 1.1975061796660293,
"learning_rate": 4.6707971066362324e-07,
"loss": 0.1478,
"step": 1149
},
{
"epoch": 1.7241379310344827,
"grad_norm": 1.3052713668217368,
"learning_rate": 4.6212290164521554e-07,
"loss": 0.0999,
"step": 1150
},
{
"epoch": 1.7256371814092955,
"grad_norm": 1.2829200350492116,
"learning_rate": 4.5719126015796757e-07,
"loss": 0.1134,
"step": 1151
},
{
"epoch": 1.7271364317841078,
"grad_norm": 1.1951762394742782,
"learning_rate": 4.522848135532698e-07,
"loss": 0.1219,
"step": 1152
},
{
"epoch": 1.7286356821589206,
"grad_norm": 1.3374337951755992,
"learning_rate": 4.474035890427769e-07,
"loss": 0.1258,
"step": 1153
},
{
"epoch": 1.7301349325337332,
"grad_norm": 1.32898947924815,
"learning_rate": 4.4254761369825984e-07,
"loss": 0.1345,
"step": 1154
},
{
"epoch": 1.7316341829085458,
"grad_norm": 1.070105003018245,
"learning_rate": 4.377169144514554e-07,
"loss": 0.1047,
"step": 1155
},
{
"epoch": 1.7331334332833583,
"grad_norm": 1.1682636360227918,
"learning_rate": 4.329115180939164e-07,
"loss": 0.1316,
"step": 1156
},
{
"epoch": 1.734632683658171,
"grad_norm": 1.0730222956223425,
"learning_rate": 4.281314512768625e-07,
"loss": 0.0733,
"step": 1157
},
{
"epoch": 1.7361319340329835,
"grad_norm": 1.5804182103141131,
"learning_rate": 4.2337674051103504e-07,
"loss": 0.1602,
"step": 1158
},
{
"epoch": 1.737631184407796,
"grad_norm": 1.2969717611999283,
"learning_rate": 4.186474121665468e-07,
"loss": 0.1239,
"step": 1159
},
{
"epoch": 1.7391304347826086,
"grad_norm": 1.1976197818859535,
"learning_rate": 4.139434924727359e-07,
"loss": 0.0965,
"step": 1160
},
{
"epoch": 1.7406296851574212,
"grad_norm": 1.1648706115112097,
"learning_rate": 4.092650075180232e-07,
"loss": 0.1332,
"step": 1161
},
{
"epoch": 1.742128935532234,
"grad_norm": 1.1483385365618108,
"learning_rate": 4.046119832497658e-07,
"loss": 0.1285,
"step": 1162
},
{
"epoch": 1.7436281859070464,
"grad_norm": 1.3131861334486878,
"learning_rate": 3.9998444547411255e-07,
"loss": 0.1161,
"step": 1163
},
{
"epoch": 1.7451274362818592,
"grad_norm": 1.1768484897582416,
"learning_rate": 3.9538241985586144e-07,
"loss": 0.0885,
"step": 1164
},
{
"epoch": 1.7466266866566715,
"grad_norm": 1.4521716297121547,
"learning_rate": 3.908059319183194e-07,
"loss": 0.1409,
"step": 1165
},
{
"epoch": 1.7481259370314843,
"grad_norm": 1.1865511424057595,
"learning_rate": 3.8625500704315645e-07,
"loss": 0.1146,
"step": 1166
},
{
"epoch": 1.7496251874062967,
"grad_norm": 1.3202950022306146,
"learning_rate": 3.8172967047026834e-07,
"loss": 0.1349,
"step": 1167
},
{
"epoch": 1.7511244377811095,
"grad_norm": 1.1629942164700995,
"learning_rate": 3.7722994729763427e-07,
"loss": 0.1424,
"step": 1168
},
{
"epoch": 1.752623688155922,
"grad_norm": 1.6394312143624425,
"learning_rate": 3.7275586248118114e-07,
"loss": 0.1696,
"step": 1169
},
{
"epoch": 1.7541229385307346,
"grad_norm": 1.3545142591470036,
"learning_rate": 3.683074408346404e-07,
"loss": 0.123,
"step": 1170
},
{
"epoch": 1.7556221889055472,
"grad_norm": 1.3704498094678754,
"learning_rate": 3.6388470702941436e-07,
"loss": 0.1229,
"step": 1171
},
{
"epoch": 1.7571214392803598,
"grad_norm": 1.3884693498795073,
"learning_rate": 3.594876855944385e-07,
"loss": 0.1246,
"step": 1172
},
{
"epoch": 1.7586206896551724,
"grad_norm": 1.2837215251778884,
"learning_rate": 3.5511640091604293e-07,
"loss": 0.1102,
"step": 1173
},
{
"epoch": 1.760119940029985,
"grad_norm": 1.1124723835788903,
"learning_rate": 3.50770877237821e-07,
"loss": 0.1328,
"step": 1174
},
{
"epoch": 1.7616191904047978,
"grad_norm": 1.3075248966429014,
"learning_rate": 3.4645113866049187e-07,
"loss": 0.1125,
"step": 1175
},
{
"epoch": 1.76311844077961,
"grad_norm": 1.1844091810957376,
"learning_rate": 3.42157209141768e-07,
"loss": 0.1115,
"step": 1176
},
{
"epoch": 1.764617691154423,
"grad_norm": 1.3020603364870487,
"learning_rate": 3.3788911249622194e-07,
"loss": 0.1083,
"step": 1177
},
{
"epoch": 1.7661169415292353,
"grad_norm": 1.3699853063123961,
"learning_rate": 3.336468723951558e-07,
"loss": 0.1108,
"step": 1178
},
{
"epoch": 1.767616191904048,
"grad_norm": 1.318514604562699,
"learning_rate": 3.294305123664665e-07,
"loss": 0.1192,
"step": 1179
},
{
"epoch": 1.7691154422788604,
"grad_norm": 1.2849230237090068,
"learning_rate": 3.2524005579452014e-07,
"loss": 0.1462,
"step": 1180
},
{
"epoch": 1.7706146926536732,
"grad_norm": 1.362630355556451,
"learning_rate": 3.2107552592001657e-07,
"loss": 0.1347,
"step": 1181
},
{
"epoch": 1.7721139430284858,
"grad_norm": 1.0899083745180387,
"learning_rate": 3.169369458398652e-07,
"loss": 0.1022,
"step": 1182
},
{
"epoch": 1.7736131934032984,
"grad_norm": 1.1474712141157715,
"learning_rate": 3.128243385070562e-07,
"loss": 0.1482,
"step": 1183
},
{
"epoch": 1.775112443778111,
"grad_norm": 1.3327556649923809,
"learning_rate": 3.087377267305297e-07,
"loss": 0.1199,
"step": 1184
},
{
"epoch": 1.7766116941529235,
"grad_norm": 1.2030608973878787,
"learning_rate": 3.0467713317505363e-07,
"loss": 0.1154,
"step": 1185
},
{
"epoch": 1.778110944527736,
"grad_norm": 1.2289757672880781,
"learning_rate": 3.006425803610963e-07,
"loss": 0.1471,
"step": 1186
},
{
"epoch": 1.7796101949025487,
"grad_norm": 1.3848742717676306,
"learning_rate": 2.9663409066470025e-07,
"loss": 0.14,
"step": 1187
},
{
"epoch": 1.7811094452773615,
"grad_norm": 1.2995838193504912,
"learning_rate": 2.9265168631736005e-07,
"loss": 0.1807,
"step": 1188
},
{
"epoch": 1.7826086956521738,
"grad_norm": 1.2992697361485803,
"learning_rate": 2.88695389405898e-07,
"loss": 0.1135,
"step": 1189
},
{
"epoch": 1.7841079460269866,
"grad_norm": 1.2182466150680802,
"learning_rate": 2.8476522187234177e-07,
"loss": 0.1033,
"step": 1190
},
{
"epoch": 1.785607196401799,
"grad_norm": 1.3597433992401198,
"learning_rate": 2.808612055138038e-07,
"loss": 0.1485,
"step": 1191
},
{
"epoch": 1.7871064467766118,
"grad_norm": 1.1444722566417072,
"learning_rate": 2.76983361982357e-07,
"loss": 0.084,
"step": 1192
},
{
"epoch": 1.7886056971514241,
"grad_norm": 1.3140225303819648,
"learning_rate": 2.731317127849209e-07,
"loss": 0.1319,
"step": 1193
},
{
"epoch": 1.790104947526237,
"grad_norm": 1.216553485628249,
"learning_rate": 2.693062792831358e-07,
"loss": 0.1359,
"step": 1194
},
{
"epoch": 1.7916041979010495,
"grad_norm": 1.1938471721227324,
"learning_rate": 2.655070826932471e-07,
"loss": 0.138,
"step": 1195
},
{
"epoch": 1.793103448275862,
"grad_norm": 1.4341104020897726,
"learning_rate": 2.617341440859883e-07,
"loss": 0.1279,
"step": 1196
},
{
"epoch": 1.7946026986506747,
"grad_norm": 1.125892799179141,
"learning_rate": 2.5798748438646326e-07,
"loss": 0.1115,
"step": 1197
},
{
"epoch": 1.7961019490254873,
"grad_norm": 1.2093194389466178,
"learning_rate": 2.5426712437403134e-07,
"loss": 0.1551,
"step": 1198
},
{
"epoch": 1.7976011994002998,
"grad_norm": 1.3263745745983149,
"learning_rate": 2.5057308468218913e-07,
"loss": 0.1344,
"step": 1199
},
{
"epoch": 1.7991004497751124,
"grad_norm": 1.0679960865391493,
"learning_rate": 2.4690538579845933e-07,
"loss": 0.0979,
"step": 1200
},
{
"epoch": 1.7991004497751124,
"eval_loss": 0.30179548263549805,
"eval_runtime": 9.527,
"eval_samples_per_second": 5.668,
"eval_steps_per_second": 1.47,
"step": 1200
},
{
"epoch": 1.800599700149925,
"grad_norm": 1.2548465774808946,
"learning_rate": 2.432640480642756e-07,
"loss": 0.141,
"step": 1201
},
{
"epoch": 1.8020989505247376,
"grad_norm": 1.3193477541908551,
"learning_rate": 2.396490916748706e-07,
"loss": 0.1287,
"step": 1202
},
{
"epoch": 1.8035982008995504,
"grad_norm": 1.6176845762647734,
"learning_rate": 2.360605366791624e-07,
"loss": 0.1889,
"step": 1203
},
{
"epoch": 1.8050974512743627,
"grad_norm": 1.4269444651213539,
"learning_rate": 2.32498402979644e-07,
"loss": 0.1881,
"step": 1204
},
{
"epoch": 1.8065967016491755,
"grad_norm": 1.2071099836238353,
"learning_rate": 2.2896271033227392e-07,
"loss": 0.131,
"step": 1205
},
{
"epoch": 1.8080959520239879,
"grad_norm": 1.1514881094574225,
"learning_rate": 2.2545347834636632e-07,
"loss": 0.1304,
"step": 1206
},
{
"epoch": 1.8095952023988007,
"grad_norm": 1.3177309667368113,
"learning_rate": 2.219707264844806e-07,
"loss": 0.1271,
"step": 1207
},
{
"epoch": 1.811094452773613,
"grad_norm": 1.0853052450972838,
"learning_rate": 2.1851447406231573e-07,
"loss": 0.0952,
"step": 1208
},
{
"epoch": 1.8125937031484258,
"grad_norm": 1.2367474251829673,
"learning_rate": 2.1508474024860171e-07,
"loss": 0.1622,
"step": 1209
},
{
"epoch": 1.8140929535232384,
"grad_norm": 1.2014308008359469,
"learning_rate": 2.1168154406499275e-07,
"loss": 0.0989,
"step": 1210
},
{
"epoch": 1.815592203898051,
"grad_norm": 1.3664210948620326,
"learning_rate": 2.0830490438596418e-07,
"loss": 0.0989,
"step": 1211
},
{
"epoch": 1.8170914542728636,
"grad_norm": 1.2102328949823467,
"learning_rate": 2.0495483993870578e-07,
"loss": 0.1065,
"step": 1212
},
{
"epoch": 1.8185907046476761,
"grad_norm": 1.2603909868780268,
"learning_rate": 2.0163136930301696e-07,
"loss": 0.1115,
"step": 1213
},
{
"epoch": 1.8200899550224887,
"grad_norm": 1.456216277877769,
"learning_rate": 1.9833451091120727e-07,
"loss": 0.1177,
"step": 1214
},
{
"epoch": 1.8215892053973013,
"grad_norm": 1.2505048564143828,
"learning_rate": 1.9506428304799095e-07,
"loss": 0.141,
"step": 1215
},
{
"epoch": 1.823088455772114,
"grad_norm": 1.3694848424018637,
"learning_rate": 1.9182070385038555e-07,
"loss": 0.1405,
"step": 1216
},
{
"epoch": 1.8245877061469264,
"grad_norm": 1.048987366714346,
"learning_rate": 1.886037913076144e-07,
"loss": 0.1086,
"step": 1217
},
{
"epoch": 1.8260869565217392,
"grad_norm": 1.2653363492592689,
"learning_rate": 1.8541356326100436e-07,
"loss": 0.1382,
"step": 1218
},
{
"epoch": 1.8275862068965516,
"grad_norm": 1.4400532322750428,
"learning_rate": 1.8225003740388546e-07,
"loss": 0.1255,
"step": 1219
},
{
"epoch": 1.8290854572713644,
"grad_norm": 1.2654798569923909,
"learning_rate": 1.791132312814975e-07,
"loss": 0.1337,
"step": 1220
},
{
"epoch": 1.8305847076461768,
"grad_norm": 1.272505866713752,
"learning_rate": 1.760031622908881e-07,
"loss": 0.1336,
"step": 1221
},
{
"epoch": 1.8320839580209896,
"grad_norm": 1.3768727400043463,
"learning_rate": 1.729198476808186e-07,
"loss": 0.1116,
"step": 1222
},
{
"epoch": 1.8335832083958021,
"grad_norm": 1.4327873874160153,
"learning_rate": 1.6986330455166733e-07,
"loss": 0.1401,
"step": 1223
},
{
"epoch": 1.8350824587706147,
"grad_norm": 1.5102663690913205,
"learning_rate": 1.6683354985533583e-07,
"loss": 0.1238,
"step": 1224
},
{
"epoch": 1.8365817091454273,
"grad_norm": 1.3851371852522554,
"learning_rate": 1.6383060039515343e-07,
"loss": 0.0965,
"step": 1225
},
{
"epoch": 1.8380809595202399,
"grad_norm": 1.4159707749484591,
"learning_rate": 1.6085447282578548e-07,
"loss": 0.1411,
"step": 1226
},
{
"epoch": 1.8395802098950524,
"grad_norm": 1.287975739004606,
"learning_rate": 1.579051836531409e-07,
"loss": 0.1176,
"step": 1227
},
{
"epoch": 1.841079460269865,
"grad_norm": 1.3107136778886062,
"learning_rate": 1.5498274923427925e-07,
"loss": 0.1102,
"step": 1228
},
{
"epoch": 1.8425787106446778,
"grad_norm": 1.1592300505162423,
"learning_rate": 1.5208718577732096e-07,
"loss": 0.1475,
"step": 1229
},
{
"epoch": 1.8440779610194902,
"grad_norm": 1.2527400216216011,
"learning_rate": 1.4921850934135785e-07,
"loss": 0.1372,
"step": 1230
},
{
"epoch": 1.845577211394303,
"grad_norm": 1.5762265876963002,
"learning_rate": 1.463767358363627e-07,
"loss": 0.1481,
"step": 1231
},
{
"epoch": 1.8470764617691153,
"grad_norm": 1.4664669932819818,
"learning_rate": 1.4356188102310266e-07,
"loss": 0.1357,
"step": 1232
},
{
"epoch": 1.8485757121439281,
"grad_norm": 1.1474255099409505,
"learning_rate": 1.4077396051305093e-07,
"loss": 0.1248,
"step": 1233
},
{
"epoch": 1.8500749625187405,
"grad_norm": 1.1751469367983083,
"learning_rate": 1.3801298976830025e-07,
"loss": 0.1021,
"step": 1234
},
{
"epoch": 1.8515742128935533,
"grad_norm": 1.3128571811676382,
"learning_rate": 1.3527898410147677e-07,
"loss": 0.12,
"step": 1235
},
{
"epoch": 1.8530734632683659,
"grad_norm": 1.2988630632224651,
"learning_rate": 1.325719586756563e-07,
"loss": 0.1141,
"step": 1236
},
{
"epoch": 1.8545727136431784,
"grad_norm": 1.1587056530261566,
"learning_rate": 1.2989192850427933e-07,
"loss": 0.1245,
"step": 1237
},
{
"epoch": 1.856071964017991,
"grad_norm": 1.327393545077868,
"learning_rate": 1.2723890845106723e-07,
"loss": 0.1399,
"step": 1238
},
{
"epoch": 1.8575712143928036,
"grad_norm": 1.3572133675205014,
"learning_rate": 1.2461291322994118e-07,
"loss": 0.1415,
"step": 1239
},
{
"epoch": 1.8590704647676162,
"grad_norm": 1.3310189409688409,
"learning_rate": 1.2201395740493948e-07,
"loss": 0.1379,
"step": 1240
},
{
"epoch": 1.8605697151424287,
"grad_norm": 1.3442947125295035,
"learning_rate": 1.1944205539013708e-07,
"loss": 0.0987,
"step": 1241
},
{
"epoch": 1.8620689655172413,
"grad_norm": 1.0798614239003894,
"learning_rate": 1.1689722144956672e-07,
"loss": 0.1254,
"step": 1242
},
{
"epoch": 1.863568215892054,
"grad_norm": 1.3849846333193567,
"learning_rate": 1.1437946969713731e-07,
"loss": 0.1307,
"step": 1243
},
{
"epoch": 1.8650674662668667,
"grad_norm": 1.2406963107705151,
"learning_rate": 1.1188881409655849e-07,
"loss": 0.122,
"step": 1244
},
{
"epoch": 1.866566716641679,
"grad_norm": 1.7565277555942336,
"learning_rate": 1.0942526846126122e-07,
"loss": 0.1617,
"step": 1245
},
{
"epoch": 1.8680659670164919,
"grad_norm": 1.2480658553182324,
"learning_rate": 1.0698884645432117e-07,
"loss": 0.1274,
"step": 1246
},
{
"epoch": 1.8695652173913042,
"grad_norm": 1.1819736586926606,
"learning_rate": 1.0457956158838545e-07,
"loss": 0.0818,
"step": 1247
},
{
"epoch": 1.871064467766117,
"grad_norm": 1.2563892910427237,
"learning_rate": 1.0219742722559433e-07,
"loss": 0.1312,
"step": 1248
},
{
"epoch": 1.8725637181409296,
"grad_norm": 1.22752437876397,
"learning_rate": 9.984245657750857e-08,
"loss": 0.1162,
"step": 1249
},
{
"epoch": 1.8740629685157422,
"grad_norm": 1.9104186055248886,
"learning_rate": 9.751466270503718e-08,
"loss": 0.1544,
"step": 1250
},
{
"epoch": 1.8755622188905547,
"grad_norm": 1.3662734745770317,
"learning_rate": 9.521405851836252e-08,
"loss": 0.1422,
"step": 1251
},
{
"epoch": 1.8770614692653673,
"grad_norm": 1.5428546343885159,
"learning_rate": 9.294065677687202e-08,
"loss": 0.1372,
"step": 1252
},
{
"epoch": 1.87856071964018,
"grad_norm": 1.3205546017262328,
"learning_rate": 9.069447008908383e-08,
"loss": 0.1567,
"step": 1253
},
{
"epoch": 1.8800599700149925,
"grad_norm": 1.1364342529541331,
"learning_rate": 8.847551091257956e-08,
"loss": 0.1362,
"step": 1254
},
{
"epoch": 1.881559220389805,
"grad_norm": 1.3084944855439842,
"learning_rate": 8.62837915539344e-08,
"loss": 0.1198,
"step": 1255
},
{
"epoch": 1.8830584707646176,
"grad_norm": 1.1852869544003721,
"learning_rate": 8.411932416864832e-08,
"loss": 0.1116,
"step": 1256
},
{
"epoch": 1.8845577211394304,
"grad_norm": 1.3425131194386866,
"learning_rate": 8.198212076107881e-08,
"loss": 0.1502,
"step": 1257
},
{
"epoch": 1.8860569715142428,
"grad_norm": 1.2585048914618981,
"learning_rate": 7.987219318437489e-08,
"loss": 0.1159,
"step": 1258
},
{
"epoch": 1.8875562218890556,
"grad_norm": 1.4671143201623167,
"learning_rate": 7.778955314041103e-08,
"loss": 0.136,
"step": 1259
},
{
"epoch": 1.889055472263868,
"grad_norm": 1.4222474463490127,
"learning_rate": 7.573421217972222e-08,
"loss": 0.1425,
"step": 1260
},
{
"epoch": 1.8905547226386807,
"grad_norm": 1.282048667403304,
"learning_rate": 7.370618170144062e-08,
"loss": 0.1247,
"step": 1261
},
{
"epoch": 1.892053973013493,
"grad_norm": 1.2302405421730362,
"learning_rate": 7.170547295323016e-08,
"loss": 0.1145,
"step": 1262
},
{
"epoch": 1.893553223388306,
"grad_norm": 1.146980393796333,
"learning_rate": 6.973209703122652e-08,
"loss": 0.0961,
"step": 1263
},
{
"epoch": 1.8950524737631185,
"grad_norm": 1.335536733481989,
"learning_rate": 6.778606487997496e-08,
"loss": 0.1571,
"step": 1264
},
{
"epoch": 1.896551724137931,
"grad_norm": 1.4027093269543287,
"learning_rate": 6.58673872923693e-08,
"loss": 0.1327,
"step": 1265
},
{
"epoch": 1.8980509745127436,
"grad_norm": 1.2697648842309783,
"learning_rate": 6.397607490959134e-08,
"loss": 0.1139,
"step": 1266
},
{
"epoch": 1.8995502248875562,
"grad_norm": 1.5571037886598633,
"learning_rate": 6.211213822105378e-08,
"loss": 0.1305,
"step": 1267
},
{
"epoch": 1.9010494752623688,
"grad_norm": 1.5640480934714973,
"learning_rate": 6.027558756434015e-08,
"loss": 0.1243,
"step": 1268
},
{
"epoch": 1.9025487256371814,
"grad_norm": 1.2348088893423754,
"learning_rate": 5.846643312514888e-08,
"loss": 0.1102,
"step": 1269
},
{
"epoch": 1.9040479760119942,
"grad_norm": 1.319087946032606,
"learning_rate": 5.668468493723489e-08,
"loss": 0.1034,
"step": 1270
},
{
"epoch": 1.9055472263868065,
"grad_norm": 1.230510294470354,
"learning_rate": 5.4930352882357486e-08,
"loss": 0.1033,
"step": 1271
},
{
"epoch": 1.9070464767616193,
"grad_norm": 1.5146473743987154,
"learning_rate": 5.3203446690220374e-08,
"loss": 0.1583,
"step": 1272
},
{
"epoch": 1.9085457271364317,
"grad_norm": 1.2323703018536982,
"learning_rate": 5.1503975938422824e-08,
"loss": 0.0985,
"step": 1273
},
{
"epoch": 1.9100449775112445,
"grad_norm": 1.2597644982920362,
"learning_rate": 4.983195005240415e-08,
"loss": 0.124,
"step": 1274
},
{
"epoch": 1.9115442278860568,
"grad_norm": 1.3027649075236873,
"learning_rate": 4.8187378305390994e-08,
"loss": 0.1342,
"step": 1275
},
{
"epoch": 1.9130434782608696,
"grad_norm": 1.284494594319255,
"learning_rate": 4.657026981834623e-08,
"loss": 0.1079,
"step": 1276
},
{
"epoch": 1.9145427286356822,
"grad_norm": 1.3563437540114411,
"learning_rate": 4.498063355991955e-08,
"loss": 0.111,
"step": 1277
},
{
"epoch": 1.9160419790104948,
"grad_norm": 1.2218664214432449,
"learning_rate": 4.341847834639645e-08,
"loss": 0.111,
"step": 1278
},
{
"epoch": 1.9175412293853074,
"grad_norm": 1.6304107772874457,
"learning_rate": 4.188381284164933e-08,
"loss": 0.1605,
"step": 1279
},
{
"epoch": 1.91904047976012,
"grad_norm": 1.2895628153813035,
"learning_rate": 4.0376645557090864e-08,
"loss": 0.1126,
"step": 1280
},
{
"epoch": 1.9205397301349325,
"grad_norm": 1.2067891403881137,
"learning_rate": 3.889698485162463e-08,
"loss": 0.1041,
"step": 1281
},
{
"epoch": 1.922038980509745,
"grad_norm": 1.308614088980277,
"learning_rate": 3.744483893160067e-08,
"loss": 0.1636,
"step": 1282
},
{
"epoch": 1.9235382308845579,
"grad_norm": 1.2190048654582166,
"learning_rate": 3.602021585076942e-08,
"loss": 0.1134,
"step": 1283
},
{
"epoch": 1.9250374812593702,
"grad_norm": 1.430236210435848,
"learning_rate": 3.462312351023567e-08,
"loss": 0.1522,
"step": 1284
},
{
"epoch": 1.926536731634183,
"grad_norm": 1.3582666782393593,
"learning_rate": 3.325356965841686e-08,
"loss": 0.0993,
"step": 1285
},
{
"epoch": 1.9280359820089954,
"grad_norm": 1.2141944277630785,
"learning_rate": 3.191156189099931e-08,
"loss": 0.1423,
"step": 1286
},
{
"epoch": 1.9295352323838082,
"grad_norm": 1.2585188964273484,
"learning_rate": 3.0597107650894855e-08,
"loss": 0.1475,
"step": 1287
},
{
"epoch": 1.9310344827586206,
"grad_norm": 1.5025901907220542,
"learning_rate": 2.9310214228202016e-08,
"loss": 0.1357,
"step": 1288
},
{
"epoch": 1.9325337331334334,
"grad_norm": 1.280230397183545,
"learning_rate": 2.8050888760163265e-08,
"loss": 0.1023,
"step": 1289
},
{
"epoch": 1.934032983508246,
"grad_norm": 1.421439477267354,
"learning_rate": 2.6819138231126695e-08,
"loss": 0.1756,
"step": 1290
},
{
"epoch": 1.9355322338830585,
"grad_norm": 1.3176598104321589,
"learning_rate": 2.5614969472506634e-08,
"loss": 0.1499,
"step": 1291
},
{
"epoch": 1.937031484257871,
"grad_norm": 1.174015790686038,
"learning_rate": 2.4438389162746434e-08,
"loss": 0.13,
"step": 1292
},
{
"epoch": 1.9385307346326837,
"grad_norm": 1.114311549268444,
"learning_rate": 2.3289403827281287e-08,
"loss": 0.1021,
"step": 1293
},
{
"epoch": 1.9400299850074962,
"grad_norm": 1.328198982585985,
"learning_rate": 2.2168019838501032e-08,
"loss": 0.1455,
"step": 1294
},
{
"epoch": 1.9415292353823088,
"grad_norm": 1.2450841353115827,
"learning_rate": 2.1074243415716288e-08,
"loss": 0.1004,
"step": 1295
},
{
"epoch": 1.9430284857571214,
"grad_norm": 1.377648309409005,
"learning_rate": 2.0008080625124048e-08,
"loss": 0.1412,
"step": 1296
},
{
"epoch": 1.944527736131934,
"grad_norm": 1.1196841017122345,
"learning_rate": 1.896953737977103e-08,
"loss": 0.0949,
"step": 1297
},
{
"epoch": 1.9460269865067468,
"grad_norm": 1.2728112916715932,
"learning_rate": 1.7958619439524817e-08,
"loss": 0.1464,
"step": 1298
},
{
"epoch": 1.9475262368815591,
"grad_norm": 1.4650226667705646,
"learning_rate": 1.6975332411040547e-08,
"loss": 0.1123,
"step": 1299
},
{
"epoch": 1.949025487256372,
"grad_norm": 1.328935000820398,
"learning_rate": 1.601968174772761e-08,
"loss": 0.1176,
"step": 1300
},
{
"epoch": 1.9505247376311843,
"grad_norm": 1.2616991198048613,
"learning_rate": 1.5091672749723564e-08,
"loss": 0.1184,
"step": 1301
},
{
"epoch": 1.952023988005997,
"grad_norm": 1.4239725782247015,
"learning_rate": 1.4191310563860806e-08,
"loss": 0.1243,
"step": 1302
},
{
"epoch": 1.9535232383808094,
"grad_norm": 1.108235535231577,
"learning_rate": 1.331860018363995e-08,
"loss": 0.0854,
"step": 1303
},
{
"epoch": 1.9550224887556222,
"grad_norm": 1.311555327325946,
"learning_rate": 1.2473546449203178e-08,
"loss": 0.1482,
"step": 1304
},
{
"epoch": 1.9565217391304348,
"grad_norm": 1.0887766055425887,
"learning_rate": 1.1656154047303691e-08,
"loss": 0.1084,
"step": 1305
},
{
"epoch": 1.9580209895052474,
"grad_norm": 1.2437187712441724,
"learning_rate": 1.0866427511285194e-08,
"loss": 0.1065,
"step": 1306
},
{
"epoch": 1.95952023988006,
"grad_norm": 1.2558811609983191,
"learning_rate": 1.0104371221050236e-08,
"loss": 0.0933,
"step": 1307
},
{
"epoch": 1.9610194902548725,
"grad_norm": 1.0793835290254463,
"learning_rate": 9.369989403041347e-09,
"loss": 0.0917,
"step": 1308
},
{
"epoch": 1.9625187406296851,
"grad_norm": 1.3376354462141502,
"learning_rate": 8.663286130216608e-09,
"loss": 0.1588,
"step": 1309
},
{
"epoch": 1.9640179910044977,
"grad_norm": 1.4377579871555195,
"learning_rate": 7.984265322023011e-09,
"loss": 0.1166,
"step": 1310
},
{
"epoch": 1.9655172413793105,
"grad_norm": 1.185812542463257,
"learning_rate": 7.332930744380906e-09,
"loss": 0.1413,
"step": 1311
},
{
"epoch": 1.9670164917541229,
"grad_norm": 1.4281481200200825,
"learning_rate": 6.709286009657368e-09,
"loss": 0.1415,
"step": 1312
},
{
"epoch": 1.9685157421289357,
"grad_norm": 1.2710000977808737,
"learning_rate": 6.1133345766511975e-09,
"loss": 0.1858,
"step": 1313
},
{
"epoch": 1.970014992503748,
"grad_norm": 1.3918057104368156,
"learning_rate": 5.5450797505690605e-09,
"loss": 0.1392,
"step": 1314
},
{
"epoch": 1.9715142428785608,
"grad_norm": 1.5876713361222057,
"learning_rate": 5.004524683011048e-09,
"loss": 0.1403,
"step": 1315
},
{
"epoch": 1.9730134932533732,
"grad_norm": 1.3874352873294997,
"learning_rate": 4.491672371950695e-09,
"loss": 0.1496,
"step": 1316
},
{
"epoch": 1.974512743628186,
"grad_norm": 1.1940229101877402,
"learning_rate": 4.0065256617199954e-09,
"loss": 0.1035,
"step": 1317
},
{
"epoch": 1.9760119940029985,
"grad_norm": 1.3546540706865013,
"learning_rate": 3.5490872429910784e-09,
"loss": 0.1269,
"step": 1318
},
{
"epoch": 1.9775112443778111,
"grad_norm": 1.2421709629976962,
"learning_rate": 3.119359652765108e-09,
"loss": 0.1626,
"step": 1319
},
{
"epoch": 1.9790104947526237,
"grad_norm": 1.2759649380055378,
"learning_rate": 2.7173452743550767e-09,
"loss": 0.1603,
"step": 1320
},
{
"epoch": 1.9805097451274363,
"grad_norm": 1.3034843979031692,
"learning_rate": 2.343046337374144e-09,
"loss": 0.1203,
"step": 1321
},
{
"epoch": 1.9820089955022488,
"grad_norm": 1.1140010277374572,
"learning_rate": 1.9964649177223184e-09,
"loss": 0.1103,
"step": 1322
},
{
"epoch": 1.9835082458770614,
"grad_norm": 1.1570791526634117,
"learning_rate": 1.6776029375759062e-09,
"loss": 0.1017,
"step": 1323
},
{
"epoch": 1.9850074962518742,
"grad_norm": 1.6900883321369187,
"learning_rate": 1.386462165375857e-09,
"loss": 0.1708,
"step": 1324
},
{
"epoch": 1.9865067466266866,
"grad_norm": 1.15203993036366,
"learning_rate": 1.1230442158188804e-09,
"loss": 0.1116,
"step": 1325
},
{
"epoch": 1.9880059970014994,
"grad_norm": 1.4236098143929679,
"learning_rate": 8.873505498474544e-10,
"loss": 0.1164,
"step": 1326
},
{
"epoch": 1.9895052473763117,
"grad_norm": 1.3446422420784052,
"learning_rate": 6.793824746437194e-10,
"loss": 0.1543,
"step": 1327
},
{
"epoch": 1.9910044977511245,
"grad_norm": 1.3285112250078446,
"learning_rate": 4.991411436189308e-10,
"loss": 0.1227,
"step": 1328
},
{
"epoch": 1.992503748125937,
"grad_norm": 1.1267414247092749,
"learning_rate": 3.466275564101285e-10,
"loss": 0.1066,
"step": 1329
},
{
"epoch": 1.9940029985007497,
"grad_norm": 1.3312680039426206,
"learning_rate": 2.2184255887403028e-10,
"loss": 0.1394,
"step": 1330
},
{
"epoch": 1.9955022488755623,
"grad_norm": 1.1117802196396092,
"learning_rate": 1.2478684308037115e-10,
"loss": 0.1133,
"step": 1331
},
{
"epoch": 1.9970014992503748,
"grad_norm": 1.0953889316887029,
"learning_rate": 5.5460947310237435e-11,
"loss": 0.1117,
"step": 1332
},
{
"epoch": 1.9985007496251874,
"grad_norm": 1.1458111655501477,
"learning_rate": 1.3865256052181252e-11,
"loss": 0.1165,
"step": 1333
},
{
"epoch": 2.0,
"grad_norm": 1.0071991154813362,
"learning_rate": 0.0,
"loss": 0.066,
"step": 1334
},
{
"epoch": 2.0,
"step": 1334,
"total_flos": 39377831657472.0,
"train_loss": 0.2224826162912767,
"train_runtime": 4117.8607,
"train_samples_per_second": 2.588,
"train_steps_per_second": 0.324
}
],
"logging_steps": 1,
"max_steps": 1334,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 2000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 39377831657472.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}